INDEX

Explanations

words related to political moderation

oai_token-act-pair · gpt-3.5-turbo

references to the term "moderate" 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 @ 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

arium

-0.85

raltar

-0.77

æ©

-0.72

yang

-0.71

TYPE

-0.71

ograp

-0.71

asper

-0.70

ADRA

-0.70

chy

-0.70

STON

-0.69

POSITIVE LOGITS

erate

0.96

 sized

0.88

 minded

0.84

 medi

0.77

 fare

0.77

 leaning

0.76

lees

0.71

 easing

0.69

(<

0.68

xual

0.68

Activations Density 0.025%

words related to political moderation

references to the term "moderate" in various contexts

No Comments

No Known Activations