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

chio

-0.75

 intervals

-0.69

enta

-0.68

 interval

-0.68

imental

-0.67

oria

-0.64

iken

-0.61

gau

-0.60

 Ribbon

-0.59

eches

-0.59

POSITIVE LOGITS

pedia

0.79

DEN

0.73

Adapt

0.71

SPONSORED

0.68

versions

0.67

ATH

0.67

methyl

0.64

VEN

0.63

dim

0.62

Marginal

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.