INDEX

Explanations

specific references or objects mentioned within a broader context

oai_token-act-pair · gpt-3.5-turbo

the word "which" and its frequency 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aiden

-0.82

mind

-0.71

bart

-0.70

bt

-0.68

politics

-0.68

ben

-0.66

marg

-0.66

usk

-0.65

trap

-0.65

Haunted

-0.65

POSITIVE LOGITS

soever

1.11

we

0.95

 they

0.93

he

0.91

she

0.84

 there

0.73

you

0.66

 millions

0.66

it

0.63

Activations Density 0.039%

specific references or objects mentioned within a broader context

the word "which" and its frequency in various contexts

No Comments

No Known Activations