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

ãĥ»

-0.83

ÃŃa

-0.71

 speeds

-0.64

onga

-0.62

 reprodu

-0.61

uits

-0.61

 propag

-0.61

TOR

-0.61

ties

-0.59

âģ

-0.59

POSITIVE LOGITS

seless

0.89

ricks

0.82

}}

0.78

 subsc

0.75

ourgeois

0.70

chieve

0.69

 Bers

0.69

blank

0.68

ħĭ

0.68

 Enhancement

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.