INDEX

Explanations

terms related to emphasizing something or highlighting importance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stressed" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

advertising

-0.93

acqu

-0.76

izons

-0.74

iop

-0.69

«ĺ

-0.69

Newsletter

-0.68

lymp

-0.66

Beck

-0.65

ä½ľ

-0.64

 Fairfax

-0.63

POSITIVE LOGITS

 stressed

1.04

 stressing

0.80

 stresses

0.79

stress

0.79

imaru

0.75

 stress

0.74

ko

0.73

âĶģ

0.73

 emphasized

0.72

icer

0.70

Activations Density 0.008%

terms related to emphasizing something or highlighting importance

instances of the word "stressed" in various contexts

No Comments

No Known Activations