INDEX

Explanations

No Explanations Found

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

ucky

-0.74

FORE

-0.73

 Faul

-0.73

################################

-0.72

agy

-0.71

thood

-0.71

Luck

-0.71

RFC

-0.70

rius

-0.70

 srfAttach

-0.69

POSITIVE LOGITS

 pupil

0.70

 flex

0.63

 Typh

0.62

idem

0.62

 equivalents

0.62

bet

0.62

 endorsement

0.61

 revers

0.60

ussen

0.60

 lash

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.