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

çĦ

-0.67

taker

-0.65

URA

-0.65

eez

-0.64

TIT

-0.63

 Sheep

-0.62

Russ

-0.62

ho

-0.62

 proverb

-0.61

hov

-0.61

POSITIVE LOGITS

 offence

0.66

ï¸ı

0.64

oral

0.64

nap

0.63

 hover

0.63

 lodge

0.62

stan

0.62

 deposition

0.61

kson

0.59

reply

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.