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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.77

-+-+

-0.74

Proxy

-0.73

 Byrne

-0.62

 Stre

-0.62

 contem

-0.61

ãĥĵ

-0.61

 Chance

-0.61

TextColor

-0.61

 Gilmore

-0.60

POSITIVE LOGITS

cha

0.76

toe

0.73

daq

0.72

akeru

0.71

doing

0.70

lund

0.70

IDS

0.66

CTV

0.64

fecture

0.64

ssl

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.