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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

advertising

-0.79

andra

-0.73

vantage

-0.67

+.

-0.65

jug

-0.63

 Scare

-0.63

 gelatin

-0.62

 indic

-0.61

 Cris

-0.61

 Kirin

-0.60

POSITIVE LOGITS

chenko

0.84

ault

0.77

thood

0.75

enburg

0.68

 qualified

0.66

gue

0.62

èĢħ

0.62

elines

0.62

ials

0.61

 auxiliary

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.