INDEX

Explanations

text related to physical proximity or closeness

oai_token-act-pair · gpt-3.5-turbo

phrases indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ury

-0.78

KC

-0.70

OGR

-0.69

Ļ

-0.68

ERG

-0.68

Reviewer

-0.67

ãĥ¼ãĥĨãĤ£

-0.67

Written

-0.65

Ĥª

-0.65

 Cosponsors

-0.64

POSITIVE LOGITS

 shore

0.99

sighted

0.89

shore

0.75

 schedule

0.75

 home

0.72

amaru

0.72

 perfection

0.72

 achieving

0.72

 Confederation

0.69

 highway

0.67

Activations Density 0.048%

text related to physical proximity or closeness

phrases indicating proximity or closeness

No Comments

No Known Activations