INDEX

Explanations

phrases related to political figures, specifically Hillary Clinton

oai_token-act-pair · gpt-3.5-turbo

references to Hillary Clinton and her campaign-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ï¸ı

-0.73

REE

-0.73

isu

-0.73

REL

-0.71

 appre

-0.71

orah

-0.67

jin

-0.66

essional

-0.66

ahi

-0.66

hig

-0.66

POSITIVE LOGITS

 herself

0.98

 Rodham

0.86

 aides

0.79

 Nieto

0.77

theless

0.77

 ACTIONS

0.76

 Jeanne

0.76

 McAuliffe

0.75

 Campaign

0.74

clinton

0.73

Activations Density 0.277%

phrases related to political figures, specifically Hillary Clinton

references to Hillary Clinton and her campaign-related activities

No Comments

No Known Activations