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

 anat

-0.70

ulz

-0.65

 commanded

-0.64

 slippery

-0.63

 wise

-0.63

Studio

-0.62

thy

-0.62

atsuki

-0.62

udos

-0.62

apo

-0.62

POSITIVE LOGITS

imore

0.73

 Croat

0.69

 Presbyter

0.66

byter

0.64

 Rebell

0.63

dt

0.62

uggest

0.61

 Ceres

0.61

={

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.