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

Mub

-0.87

ongo

-0.74

imens

-0.73

tnc

-0.72

ruciating

-0.71

igious

-0.71

ouf

-0.70

itudinal

-0.68

htaking

-0.68

 grap

-0.67

POSITIVE LOGITS

ETF

0.71

é¾į

0.68

ENTS

0.65

 Truman

0.65

âĶģ

0.64

 Townsend

0.64

ADA

0.62

ACP

0.61

ocobo

0.61

ATOR

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.