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

 illegally

-0.68

 somew

-0.66

ram

-0.64

 disc

-0.62

 favor

-0.62

 nails

-0.62

 fingerprints

-0.61

fug

-0.61

MPH

-0.61

 Lime

-0.60

POSITIVE LOGITS

Values

0.83

é¾

0.81

PHOTOS

0.75

Above

0.74

ELS

0.74

Chest

0.74

WER

0.72

Builder

0.72

izons

0.70

Trigger

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.