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

inth

-0.89

edIn

-0.85

 ende

-0.80

theless

-0.79

 streng

-0.78

 redes

-0.77

 destro

-0.75

 defic

-0.73

senal

-0.72

ydia

-0.72

POSITIVE LOGITS

trump

0.76

ulence

0.72

ansom

0.72

Gh

0.68

inance

0.68

rieve

0.66

lier

0.66

acting

0.65

court

0.64

 Amnesty

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.