INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

poke

-0.71

ilater

-0.69

termination

-0.66

Gat

-0.66

DEN

-0.63

bol

-0.63

kefeller

-0.62

sembly

-0.62

CAP

-0.61

 puzz

-0.61

POSITIVE LOGITS

yright

0.72

nered

0.67

 Icelandic

0.65

 handles

0.65

 harbour

0.65

iquette

0.61

 subtitles

0.61

 resists

0.61

isms

0.61

 Kraken

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.