INDEX

Explanations

mentions of personal or private aspects of individuals' lives, such as home, behavior, reactions, living conditions, work, etc

oai_token-act-pair · gpt-3.5-turbo

references to home and personal experiences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Samar

-0.68

atton

-0.66

 Guan

-0.66

©¶æ

-0.65

etheless

-0.63

asus

-0.62

 Horizon

-0.61

 myself

-0.61

 Tycoon

-0.60

 Beckham

-0.60

POSITIVE LOGITS

 selves

1.42

 counterparts

1.23

 brethren

0.85

respective

0.75

 holdings

0.75

 careers

0.74

 overl

0.71

 lives

0.71

 arsenal

0.70

 neighbours

0.70

Activations Density 0.385%

mentions of personal or private aspects of individuals' lives, such as home, behavior, reactions, living conditions, work, etc

references to home and personal experiences

No Comments

No Known Activations