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

Negative Logits

abouts

-0.79

staking

-0.75

ovich

-0.71

Rated

-0.69

overe

-0.67

cil

-0.66

eco

-0.65

 Bullets

-0.63

 princip

-0.63

bane

-0.61

POSITIVE LOGITS

 foregoing

0.72

ļ

0.62

 genitals

0.61

¶ħ

0.60

 Holo

0.60

 Known

0.60

andum

0.60

 triggering

0.60

dor

0.59

 genital

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.