INDEX

Explanations

descriptions or references to physical size

oai_token-act-pair · gpt-3.5-turbo

references to size or dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

veyard

-0.80

rea

-0.76

iring

-0.76

INTON

-0.75

ron

-0.74

ired

-0.73

pu

-0.71

endez

-0.71

nee

-0.70

rom

-0.70

POSITIVE LOGITS

 size

1.04

 scale

1.01

 sizes

0.88

 Size

0.88

 mismatch

0.83

 stature

0.83

 scales

0.81

size

0.79

 footprint

0.79

 enorm

0.79

Activations Density 0.016%

descriptions or references to physical size

references to size or dimensions

No Comments

No Known Activations