INDEX

Explanations

information related to a legal or political context

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant actions or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 CONTIN

-0.69

unless

-0.66

ERAL

-0.64

undrum

-0.63

 âĵĺ

-0.62

maxwell

-0.61

manager

-0.61

 forgiven

-0.59

 rematch

-0.58

Pak

-0.56

POSITIVE LOGITS

 earlier

1.06

 last

1.01

 yesterday

0.92

 previous

0.85

 originally

0.83

ago

0.79

 beforehand

0.78

terday

0.76

 prior

0.75

 previously

0.72

Activations Density 1.238%

information related to a legal or political context

phrases indicating significant actions or outcomes

No Comments

No Known Activations