INDEX

Explanations

mentions of specific wordings or phrases within passages that involve certain topics or products

oai_token-act-pair · gpt-3.5-turbo

items or entities that are part of a specific category or subject matter

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

psy

-0.68

ctor

-0.66

METHOD

-0.64

osi

-0.64

à©

-0.62

à¨

-0.60

 hypothesis

-0.60

ctive

-0.60

Scient

-0.59

cer

-0.59

POSITIVE LOGITS

paces

1.13

chool

0.95

hops

0.95

hips

0.91

hip

0.90

etter

0.82

mith

0.81

pace

0.81

ourcing

0.79

cius

0.78

Activations Density 0.410%

mentions of specific wordings or phrases within passages that involve certain topics or products

items or entities that are part of a specific category or subject matter

No Comments

No Known Activations