INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ner" 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 @ 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

ĸļ

-0.71

DonaldTrump

-0.64

 Occupations

-0.64

ERA

-0.63

urities

-0.62

EMP

-0.62

oral

-0.59

avorite

-0.58

wordpress

-0.57

Constructed

-0.57

POSITIVE LOGITS

getic

1.06

ding

1.01

lund

0.97

stein

0.96

gie

0.95

wald

0.91

nen

0.91

dal

0.89

sonian

0.87

stocks

0.84

Activations Density 0.039%

names of individuals or entities

occurrences of the substring "ner" in various contexts

No Comments

No Known Activations