INDEX

Explanations

phrases related to professions and titles

oai_token-act-pair · gpt-3.5-turbo

professions or roles related to individuals

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

etting

-0.89

undai

-0.82

ilion

-0.82

perm

-0.81

arching

-0.76

sembly

-0.76

ilers

-0.75

imeter

-0.72

inki

-0.72

romy

-0.70

POSITIVE LOGITS

 extraord

0.96

 Candidate

0.94

 Guides

0.92

 Tracker

0.87

 Perspect

0.85

hood

0.84

Joined

0.83

 Alley

0.82

 Mode

0.80

 Hunters

0.80

Activations Density 0.202%

phrases related to professions and titles

professions or roles related to individuals

No Comments

No Known Activations