INDEX

Explanations

website and social media elements like buttons, links or instructions

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating association or accompaniment

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

bilt

-0.81

 cheaply

-0.56

 storefront

-0.51

 botched

-0.50

 Establishment

-0.50

strate

-0.50

sov

-0.50

 shore

-0.50

 Beverly

-0.50

 attempts

-0.49

POSITIVE LOGITS

draw

1.30

drawn

1.12

holding

1.10

 regard

0.97

 regards

0.88

stood

0.86

held

0.83

 impunity

0.79

 respect

0.79

 caution

0.73

Activations Density 0.067%

website and social media elements like buttons, links or instructions

prepositions and phrases indicating association or accompaniment

No Comments

No Known Activations