INDEX

Explanations

words related to strong negative expressions or criticism

oai_token-act-pair · gpt-3.5-turbo

negative evaluations or criticisms

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

uclear

-0.76

isations

-0.70

ouf

-0.67

teness

-0.66

utherford

-0.66

Lago

-0.65

ATIONS

-0.65

ATIONAL

-0.64

isation

-0.63

nm

-0.62

POSITIVE LOGITS

 dick

1.05

sylvania

0.95

asses

0.95

 suck

0.93

eries

0.89

shit

0.84

hots

0.83

bowl

0.83

driver

0.82

loads

0.81

Activations Density 0.013%

words related to strong negative expressions or criticism

negative evaluations or criticisms

No Comments

No Known Activations