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

 Bombay

-0.73

 Shiv

-0.64

PF

-0.62

JB

-0.62

unknown

-0.61

Maz

-0.60

HC

-0.59

 Parm

-0.58

 Cham

-0.57

rypt

-0.57

POSITIVE LOGITS

perty

0.76

etting

0.72

Â¯

0.71

fters

0.71

essa

0.70

Dialogue

0.69

PLIED

0.69

peak

0.67

ancies

0.67

Ãª

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.