INDEX

Explanations

phrases indicating repeated patterns or occurrences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating repetitive actions or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

arling

-0.78

agar

-0.69

yt

-0.68

bda

-0.67

agra

-0.66

stood

-0.66

ey

-0.66

edu

-0.65

ajor

-0.64

ondon

-0.64

POSITIVE LOGITS

 someone

1.07

 somebody

1.05

soever

1.00

 imaginable

0.99

 possible

0.94

someone

0.92

 else

0.87

 conceivable

0.85

you

0.83

we

0.77

Activations Density 0.052%

phrases indicating repeated patterns or occurrences

phrases indicating repetitive actions or occurrences

No Comments

No Known Activations