INDEX

Explanations

countries or places

oai_token-act-pair · gpt-3.5-turbo

references to specific countries

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

naissance

-0.72

Discussion

-0.68

ellation

-0.63

 continu

-0.62

ularity

-0.61

heny

-0.61

 accur

-0.61

cause

-0.60

cill

-0.60

Cloud

-0.59

POSITIVE LOGITS

 Airlines

0.90

ican

0.79

 Airways

0.76

 Yard

0.74

 TODAY

0.73

borg

0.70

's

0.69

ica

0.69

 reacts

0.67

 Today

0.67

Activations Density 0.203%

countries or places

references to specific countries

No Comments

No Known Activations