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

rich

-0.78

SEA

-0.78

vous

-0.70

akedown

-0.70

ricks

-0.69

å¥

-0.65

isphere

-0.65

beck

-0.64

ibling

-0.64

 classmate

-0.63

POSITIVE LOGITS

legraph

0.77

ctuary

0.64

 susp

0.63

 suspend

0.63

('

0.62

 prev

0.61

Zur

0.61

 Medieval

0.61

:,

0.60

 conduit

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.