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

Raid

-0.69

 Marketable

-0.65

 Fiesta

-0.65

ãģ®å®

-0.63

fts

-0.61

 Norm

-0.61

 Shroud

-0.60

 Gleaming

-0.58

fs

-0.57

 Emerald

-0.57

POSITIVE LOGITS

OTO

0.64

ASED

0.63

 tradem

0.63

ech

0.62

lessly

0.61

esome

0.61

arry

0.61

igree

0.60

anders

0.58

BUT

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.