INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hire

-0.78

OE

-0.74

ISTER

-0.73

ible

-0.73

ISE

-0.72

IFF

-0.72

nir

-0.70

PsyNetMessage

-0.70

ivo

-0.68

ISION

-0.67

POSITIVE LOGITS

galitarian

0.67

¡

0.65

ĺħ

0.62

«ĺ

0.62

izont

0.62

 epit

0.61

quart

0.60

 labels

0.60

agall

0.59

gemony

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.