INDEX

Explanations

statements of fact or information in text

oai_token-act-pair · gpt-3.5-turbo

references to statements made in articles or reports

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

ipal

-0.79

iffe

-0.79

 Flavoring

-0.73

Sco

-0.68

atz

-0.66

asi

-0.65

 suscept

-0.64

cv

-0.64

rax

-0.63

xtap

-0.63

POSITIVE LOGITS

 unequivocally

0.85

 goodbye

0.81

rooms

0.78

lessness

0.70

spec

0.68

quo

0.67

less

0.67

 emphatically

0.66

pec

0.65

ulate

0.65

Activations Density 0.028%

statements of fact or information in text

references to statements made in articles or reports

No Comments

No Known Activations