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

phasis

-0.73

 subt

-0.72

 asserts

-0.70

 faults

-0.69

 encomp

-0.68

elo

-0.68

 executed

-0.65

 Bened

-0.64

 theorem

-0.63

 wills

-0.63

POSITIVE LOGITS

aby

0.75

\":

0.73

KEN

0.72

OHN

0.71

>>>>>>>>

0.70

Pak

0.67

photo

0.67

MH

0.67

Introduced

0.66

agh

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.