INDEX

Explanations

statements made by authorities or police

oai_token-act-pair · gpt-3.5-turbo

mentions of authorities and official reports related to incidents

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

²¾

-0.72

eday

-0.71

ggle

-0.69

dule

-0.68

ploma

-0.62

 Subtle

-0.62

oros

-0.60

OOOOOOOO

-0.60

Grad

-0.59

chrome

-0.57

POSITIVE LOGITS

 spokeswoman

0.88

 spokesman

0.83

 said

0.82

said

0.74

SAY

0.72

 correspondent

0.70

 REUTERS

0.70

 issuer

0.68

 sugg

0.68

 says

0.67

Activations Density 0.438%

statements made by authorities or police

mentions of authorities and official reports related to incidents

No Comments

No Known Activations