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

credit

-0.70

nih

-0.66

rev

-0.66

batch

-0.65

ships

-0.65

 Caption

-0.63

risis

-0.63

 mortg

-0.62

iatus

-0.62

 typo

-0.61

POSITIVE LOGITS

Mik

0.74

atan

0.72

 Kappa

0.70

 Takeru

0.70

 Meier

0.70

othy

0.69

eton

0.65

emet

0.64

 accommodating

0.63

icho

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.