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

 Courier

-0.72

SPONSORED

-0.70

utton

-0.68

 craw

-0.66

 HuffPost

-0.62

 fres

-0.61

 slic

-0.60

rity

-0.60

 sermon

-0.60

 quickest

-0.59

POSITIVE LOGITS

ãĤ©

0.84

ãĥ£

0.78

DX

0.71

å°Ĩ

0.70

axis

0.70

hal

0.69

banks

0.69

MFT

0.68

DEM

0.68

uden

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.