INDEX

Explanations

phrases indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "perhaps" indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iak

-0.81

bender

-0.79

elight

-0.76

ioch

-0.74

chens

-0.73

shit

-0.71

ombat

-0.71

sbm

-0.71

eworld

-0.71

etime

-0.70

POSITIVE LOGITS

haps

1.01

 unsurprisingly

0.86

 someday

0.86

 sensing

0.73

 opio

0.70

 quir

0.67

 exacerbated

0.67

 embold

0.67

 unintentionally

0.66

 unemploy

0.66

Activations Density 0.022%

phrases indicating emphasis or importance

instances of the word "perhaps" indicating uncertainty or speculation

No Comments

No Known Activations