INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

aea

-0.76

ijn

-0.75

 Preservation

-0.73

urrencies

-0.69

omsky

-0.69

 destro

-0.68

iris

-0.68

ongyang

-0.67

moil

-0.67

 è£ıè

-0.65

POSITIVE LOGITS

MLB

0.63

MGM

0.60

port

0.60

doing

0.60

 bundled

0.59

IRC

0.59

 Baird

0.58

GI

0.57

 opting

0.57

Gat

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.