INDEX

Explanations

words related to investigations or inquiries into various matters

oai_token-act-pair · gpt-3.5-turbo

terms related to investigations and crimes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Tokens

-0.94

sticks

-0.75

FIG

-0.71

keys

-0.70

ãĤª

-0.70

template

-0.69

DES

-0.67

anguage

-0.67

fighters

-0.66

SN

-0.66

POSITIVE LOGITS

 alleged

1.06

 suspected

0.98

 crimes

0.97

 wrongdoing

0.95

 wrongful

0.94

 prosecution

0.91

 criminal

0.91

 corruption

0.90

 crime

0.90

 Crimes

0.90

Activations Density 0.251%

words related to investigations or inquiries into various matters

terms related to investigations and crimes

No Comments

No Known Activations