INDEX

Explanations

structured and organized information or settings

oai_token-act-pair · gpt-3.5-turbo

terms related to organization and structure in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

flies

-0.88

yer

-0.83

lust

-0.81

alter

-0.77

ledge

-0.73

chief

-0.73

aders

-0.73

esville

-0.73

adier

-0.73

nea

-0.72

POSITIVE LOGITS

 versions

0.88

nesday

0.76

 seating

0.76

paren

0.75

 linear

0.75

ocument

0.74

rive

0.73

 subur

0.73

 leisure

0.70

BY

0.70

Activations Density 0.166%

structured and organized information or settings

terms related to organization and structure in various contexts

No Comments

No Known Activations