INDEX

Explanations

mentions of specific locations or entities

oai_token-act-pair · gpt-3.5-turbo

mentions of "bridge" and significant individuals or entities associated with it

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

matic

-1.15

matically

-0.93

atically

-0.76

eper

-0.67

cart

-0.67

sat

-0.66

sch

-0.66

gie

-0.66

 lapse

-0.65

oos

-0.64

POSITIVE LOGITS

hire

0.83

ulla

0.72

bridge

0.72

joy

0.71

assing

0.71

bent

0.67

neys

0.67

assed

0.66

Bok

0.64

rose

0.64

Activations Density 0.032%

mentions of specific locations or entities

mentions of "bridge" and significant individuals or entities associated with it

No Comments

No Known Activations