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

 Inspect

-0.72

 Cutter

-0.67

Nav

-0.67

Pru

-0.66

 motivating

-0.63

 Cipher

-0.63

avering

-0.63

ogenic

-0.62

 Mend

-0.59

Arn

-0.59

POSITIVE LOGITS

Reviewer

0.69

ilege

0.65

externalActionCode

0.65

ioch

0.64

req

0.64

uncle

0.64

ellow

0.64

ilst

0.63

ael

0.63

wcs

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.