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

 IMAGES

-0.73

UTERS

-0.66

 entities

-0.65

 oppos

-0.64

 buttocks

-0.63

 yard

-0.61

 scandals

-0.61

 Playboy

-0.60

 bast

-0.60

 CLSID

-0.59

POSITIVE LOGITS

ober

0.76

ãĤ©

0.73

aber

0.72

kowski

0.72

ima

0.71

verty

0.71

omore

0.70

reditary

0.70

raft

0.70

jam

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.