INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

okÃ©

-0.85

 eyebrows

-0.74

rals

-0.71

 Yards

-0.70

 Visitors

-0.68

 handwriting

-0.67

rase

-0.67

imming

-0.66

 Chiefs

-0.65

papers

-0.64

POSITIVE LOGITS

ECH

0.88

å¾

0.75

ÙĲ

0.73

çĦ

0.73

ãĤ¼

0.72

WARE

0.72

EMP

0.72

WARD

0.71

ãĤ¡

0.71

SPEC

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.