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

Ic

-0.73

onduct

-0.69

hot

-0.68

afety

-0.66

hare

-0.65

escape

-0.64

weather

-0.60

Dash

-0.60

onductor

-0.60

veh

-0.60

POSITIVE LOGITS

ãĤª

0.86

Ô

0.82

ãĥ©ãĥ³

0.74

ãĥ¼ãĥ«

0.73

èĢħ

0.70

©¶æ¥µ

0.69

TDs

0.69

ãĥ¼ãĥĨãĤ£

0.68

Ĥ¬

0.66

ãĤ´

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.