INDEX

Explanations

titles or roles in organizations

oai_token-act-pair · gpt-3.5-turbo

job titles or positions of authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TIME

-0.64

idden

-0.57

 Fighters

-0.56

azes

-0.55

 è£ıç

-0.55

 Witches

-0.54

lez

-0.54

IRE

-0.54

 Soldiers

-0.53

à¨

-0.53

POSITIVE LOGITS

 overseeing

0.84

 extraord

0.83

 responsible

0.81

inator

0.77

 liaison

0.75

 specializing

0.75

iliate

0.74

 emer

0.72

 negotiator

0.72

 laureate

0.70

Activations Density 0.159%

titles or roles in organizations

job titles or positions of authority

No Comments

No Known Activations