INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sbm

-0.83

srf

-0.81

actionDate

-0.78

crim

-0.78

isSpecialOrderable

-0.76

ignty

-0.75

utic

-0.72

iless

-0.72

depending

-0.70

raid

-0.69

POSITIVE LOGITS

1.10

/$

0.93

/#

0.80

/_

0.78

0.75

/?

0.69

/"

0.68

/(

0.63

 comparison

0.61

chester

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.