INDEX

Explanations

titles or roles related to various professions and organizations

oai_token-act-pair · gpt-3.5-turbo

titles or roles associated with individuals, particularly in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

zers

-0.73

cards

-0.72

 informants

-0.71

worldly

-0.71

¬¼

-0.68

 pieces

-0.66

goers

-0.65

oner

-0.65

pieces

-0.65

 recordings

-0.65

POSITIVE LOGITS

MPH

0.91

 Sierra

0.85

NCT

0.82

 USAF

0.81

 Kinnikuman

0.80

 Ministry

0.80

NEC

0.78

 Carnegie

0.75

 Dept

0.74

 Programming

0.74

Activations Density 0.132%

titles or roles related to various professions and organizations

titles or roles associated with individuals, particularly in professional contexts

No Comments

No Known Activations