INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 succeeding

-0.69

 intern

-0.65

 martial

-0.64

neau

-0.63

DERR

-0.63

tal

-0.63

angering

-0.62

 dent

-0.62

ibur

-0.61

 readiness

-0.61

POSITIVE LOGITS

Hig

0.79

Used

0.74

Times

0.70

inks

0.70

essee

0.68

Lost

0.68

Adds

0.67

angel

0.66

 Princ

0.66

Ò

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.