INDEX

Explanations

phrases indicating the act of expressing an opinion or refusal

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the act of speaking or expressing oneself

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

ockets

-0.71

gotten

-0.60

 infl

-0.59

 peninsula

-0.57

 Nanto

-0.57

 instincts

-0.56

 Peninsula

-0.56

aspx

-0.56

edia

-0.55

 Firearms

-0.54

POSITIVE LOGITS

 goodbye

1.68

 hello

1.41

 Goodbye

1.30

 farewell

1.25

hi

1.18

yes

1.11

 sorry

1.11

 aloud

1.09

 Amen

1.08

YES

0.98

Activations Density 0.119%

phrases indicating the act of expressing an opinion or refusal

phrases indicating the act of speaking or expressing oneself

No Comments

No Known Activations