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

iac

-0.72

 swall

-0.64

ribution

-0.64

ining

-0.63

 climbs

-0.63

igans

-0.62

nets

-0.62

izing

-0.61

inations

-0.61

raising

-0.61

POSITIVE LOGITS

ļé

0.89

hedral

0.74

BILITIES

0.72

 Dharma

0.71

ĳ

0.69

zzo

0.64

Fine

0.63

ãĥª

0.63

 Pearce

0.62

ÂłÂłÂł

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.