INDEX

Explanations

mentions of individuals and their affiliations or occupations

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals involved in activism or public service roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

+.

-0.86

'.

-0.72

".

-0.71

.<

-0.70

.''.

-0.70

".[

-0.69

.</

-0.68

>.

-0.67

."

-0.65

*.

-0.65

POSITIVE LOGITS

wegian

0.80

earcher

0.74

veland

0.68

itness

0.65

itone

0.61

 sociology

0.61

 supervisor

0.61

 curator

0.61

0.60

onge

0.60

Activations Density 0.547%

mentions of individuals and their affiliations or occupations

references to specific individuals involved in activism or public service roles

No Comments

No Known Activations