INDEX

Explanations

words related to political figures

oai_token-act-pair · gpt-3.5-turbo

instances of the comma punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

olars

-0.71

acters

-0.69

ocial

-0.66

versive

-0.65

eals

-0.65

isers

-0.65

inner

-0.62

atlantic

-0.62

ictional

-0.61

 offender

-0.61

POSITIVE LOGITS

0.81

Jr

0.77

paio

0.75

aka

0.72

ĪĴ

0.68

ucci

0.67

 Kard

0.67

etc

0.66

 Baird

0.65

Sr

0.65

Activations Density 0.175%

words related to political figures

instances of the comma punctuation

No Comments

No Known Activations