INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atform

-0.84

bowl

-0.71

speech

-0.71

 Speech

-0.69

ä½ľ

-0.66

sburgh

-0.66

çīĪ

-0.65

nect

-0.65

bourg

-0.65

 Pavilion

-0.65

POSITIVE LOGITS

 adolesc

0.71

erie

0.64

 volunt

0.64

 desper

0.63

 stockp

0.62

 tolerant

0.62

redo

0.62

 scient

0.61

 termin

0.60

TRY

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.