INDEX

Explanations

comparisons between different entities

oai_token-act-pair · gpt-3.5-turbo

phrases that compare two opposing concepts or entities, often in the format of "X vs. Y."

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

shire

-0.77

spot

-0.75

 liner

-0.72

oola

-0.69

bean

-0.65

Topics

-0.64

estern

-0.63

 Lauder

-0.61

tarian

-0.60

lied

-0.60

POSITIVE LOGITS

creen

0.76

illa

0.75

illas

0.74

pecting

0.74

ampa

0.71

.,

0.65

RHP

0.63

pect

0.62

seq

0.61

iors

0.60

Activations Density 0.017%

comparisons between different entities

phrases that compare two opposing concepts or entities, often in the format of "X vs. Y."

No Comments

No Known Activations