INDEX

Explanations

names of political figures and terms related to political discussions

oai_token-act-pair · gpt-3.5-turbo

references to prominent political figures, particularly Donald Trump and Barack Obama

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

etheless

-0.67

 Albion

-0.62

 Siber

-0.60

 Constantin

-0.60

 STATS

-0.59

ogie

-0.58

alogue

-0.58

semble

-0.57

pain

-0.56

 Seym

-0.56

POSITIVE LOGITS

clinton

0.95

 Presidential

0.78

 Republicans

0.76

Clinton

0.75

 presidential

0.74

 Hillary

0.73

 Election

0.72

 Clinton

0.72

 Democrats

0.72

Hillary

0.71

Activations Density 0.352%

names of political figures and terms related to political discussions

references to prominent political figures, particularly Donald Trump and Barack Obama

No Comments

No Known Activations