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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igi

-0.81

bidden

-0.79

alf

-0.74

gil

-0.73

imens

-0.72

ãĥŁ

-0.71

reetings

-0.71

ãĤŃ

-0.71

":["

-0.69

POSITIVE LOGITS

 simulator

0.66

onement

0.62

 layered

0.62

 rehe

0.62

thing

0.62

wallet

0.60

ther

0.59

CET

0.58

 oven

0.58

CV

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.