INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

etsk

-0.69

arter

-0.66

ocr

-0.65

rame

-0.65

uana

-0.63

 hemp

-0.63

arten

-0.62

 coerc

-0.60

alloc

-0.60

iann

-0.59

POSITIVE LOGITS

OPLE

0.73

 Lance

0.71

VD

0.71

 Patton

0.69

ventus

0.69

bug

0.67

 Undead

0.67

BILITIES

0.66

iple

0.66

few

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.