INDEX

Explanations

personal pronouns and phrases referring to or involving people

oai_token-act-pair · gpt-3.5-turbo

references to individuals and communities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\\\\\\\\

-0.76

rection

-0.62

PokÃ©

-0.56

roo

-0.56

potion

-0.55

 Advertisement

-0.55

 clarification

-0.55

rontal

-0.55

 sqor

-0.55

alin

-0.55

POSITIVE LOGITS

 composing

1.08

 closest

1.05

 involved

1.01

 nearest

1.00

 responsible

0.91

 surrounding

0.91

folk

0.89

 surveyed

0.87

 entrusted

0.86

responsible

0.82

Activations Density 0.298%

personal pronouns and phrases referring to or involving people

references to individuals and communities

No Comments

No Known Activations