INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Athens

-0.83

 Mubarak

-0.68

elligent

-0.66

Osw

-0.65

amera

-0.64

INA

-0.62

Scotland

-0.61

 Pradesh

-0.61

 Constantinople

-0.61

 Controls

-0.60

POSITIVE LOGITS

tailed

0.77

tails

0.77

iction

0.72

 discounts

0.71

 holidays

0.69

#$

0.69

gon

0.66

isson

0.65

haps

0.65

dyl

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.