INDEX

Explanations

phrases that involve presenting or being presented with options or choices

oai_token-act-pair · gpt-3.5-turbo

statements about choices or options presented 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rote

-0.81

urance

-0.81

efe

-0.73

cia

-0.71

NY

-0.71

mone

-0.69

advertising

-0.66

 Immunity

-0.65

amon

-0.64

 Nolan

-0.63

POSITIVE LOGITS

 depending

1.15

 either

0.91

 ranging

0.89

 choose

0.87

 varying

0.84

depending

0.82

 whichever

0.80

 customizable

0.78

 Either

0.77

 alternatively

0.77

Activations Density 0.748%

phrases that involve presenting or being presented with options or choices

statements about choices or options presented in various contexts

No Comments

No Known Activations