INDEX

Explanations

specific job titles for specific professions or roles

oai_token-act-pair · gpt-3.5-turbo

terms related to management and organizational roles

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

assian

-0.74

oven

-0.72

alach

-0.71

 Effect

-0.67

 Meal

-0.64

inational

-0.63

ablish

-0.63

enge

-0.63

ostic

-0.63

#$

-0.63

POSITIVE LOGITS

 director

0.94

 manager

0.91

 officials

0.91

 chief

0.88

 coordinator

0.88

 circles

0.86

wat

0.85

 adviser

0.84

 spokesman

0.82

 headquarters

0.81

Activations Density 0.317%

specific job titles for specific professions or roles

terms related to management and organizational roles

No Comments

No Known Activations