INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

plan

-0.75

eware

-0.67

 Europa

-0.63

atorium

-0.63

athom

-0.62

atted

-0.61

atories

-0.60

ETS

-0.60

ibaba

-0.60

iably

-0.59

POSITIVE LOGITS

 destro

0.77

clerosis

0.71

artifacts

0.66

ulhu

0.64

 Presbyter

0.64

 obstruct

0.63

 corro

0.63

dfx

0.62

earch

0.62

 widened

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.