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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulner

-0.88

enary

-0.78

ieth

-0.75

icity

-0.73

avier

-0.72

ividual

-0.69

çĶ°

-0.69

ihad

-0.67

avin

-0.66

apeake

-0.65

POSITIVE LOGITS

 Unlock

0.80

=]

0.76

uably

0.70

isSpecialOrderable

0.64

anche

0.64

 distingu

0.62

 favour

0.61

Lua

0.61

 therap

0.61

 Cantor

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.