INDEX

Explanations

words related to political figures and events

oai_token-act-pair · gpt-3.5-turbo

indicators of political engagement or activism

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

luster

-0.79

abal

-0.72

farious

-0.71

opian

-0.71

onto

-0.70

raints

-0.69

nesday

-0.67

FTWARE

-0.62

orld

-0.61

ãĤ¤ãĥĪ

-0.60

POSITIVE LOGITS

 Â·

0.76

 COURT

0.64

 âĢº

0.61

Â·

0.61

.--

0.61

 Kills

0.58

 UNCLASSIFIED

0.56

 emph

0.55

 Floyd

0.54

 âĢ¢

0.53

Activations Density 0.323%

words related to political figures and events

indicators of political engagement or activism

No Comments

No Known Activations