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

egg

-0.76

emb

-0.75

umbnail

-0.69

owan

-0.69

 disemb

-0.67

language

-0.64

fit

-0.63

atever

-0.63

ulate

-0.62

wcsstore

-0.60

POSITIVE LOGITS

seq

0.86

 cess

0.68

 Referred

0.65

nda

0.63

 hypoc

0.62

itialized

0.61

 Accessed

0.61

CAS

0.60

sal

0.59

rett

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.