INDEX

Explanations

names of political figures

oai_token-act-pair · gpt-3.5-turbo

references to specific political figures and events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.72

 catalogue

-0.68

rower

-0.66

 Ambro

-0.60

 pastoral

-0.58

 booklet

-0.58

heny

-0.58

 Jagu

-0.57

BMC

-0.57

 stub

-0.57

POSITIVE LOGITS

Hillary

0.93

 Hillary

0.85

ghazi

0.81

OTUS

0.80

 Clinton

0.75

omever

0.75

Clinton

0.75

Trump

0.75

Politics

0.73

 Pence

0.68

Activations Density 0.682%

names of political figures

references to specific political figures and events

No Comments

No Known Activations