INDEX

Explanations

evidence or statements indicating truth or correctness

oai_token-act-pair · gpt-3.5-turbo

the phrase "in fact" followed by assertions or clarifications of previous statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bye

-0.79

 Crown

-0.68

 Klux

-0.67

Cay

-0.65

South

-0.63

MENTS

-0.61

Afee

-0.61

haw

-0.59

Cmd

-0.55

 Hutchinson

-0.55

POSITIVE LOGITS

ional

0.91

uality

0.80

 unfocusedRange

0.76

ually

0.75

netflix

0.73

opus

0.73

OGR

0.73

dayName

0.71

orial

0.70

ãĥĻ

0.68

Activations Density 0.021%

evidence or statements indicating truth or correctness

the phrase "in fact" followed by assertions or clarifications of previous statements

No Comments

No Known Activations