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

]'

-0.85

inous

-0.79

enstein

-0.72

)</

-0.71

]"

-0.70

icist

-0.67

 LORD

-0.64

anyahu

-0.64

 Souls

-0.63

achev

-0.63

POSITIVE LOGITS

pport

0.80

ãĤ´ãĥ³

0.72

 Senegal

0.69

 interf

0.66

 Portugal

0.64

ãĤ¢ãĥ«

0.64

Fey

0.64

 toler

0.62

IPM

0.62

rha

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.