INDEX

Explanations

comparisons or distinctions between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

references to differences and distinctions between concepts or entities

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

ãĥĦ

-0.79

ATA

-0.79

vez

-0.76

mberg

-0.73

onz

-0.71

ãĤ®

-0.70

rive

-0.66

ãĤ±

-0.64

å°Ĩ

-0.63

ico

-0.62

POSITIVE LOGITS

 between

1.61

between

1.34

 Between

1.26

iveness

1.08

 separating

0.98

iator

0.97

ials

0.96

 maker

0.94

iating

0.90

Between

0.85

Activations Density 0.058%

comparisons or distinctions between different entities or concepts

references to differences and distinctions between concepts or entities

No Comments

No Known Activations