INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

opard

-0.75

ateral

-0.73

uci

-0.71

uca

-0.69

depend

-0.68

rite

-0.67

uge

-0.63

itic

-0.62

 appet

-0.61

rh

-0.61

POSITIVE LOGITS

zona

0.66

âĸ¬

0.62

©¶æ

0.61

 referen

0.61

çīĪ

0.61

edly

0.59

 ashes

0.58

OOL

0.58

LESS

0.58

URRENT

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.