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

enegger

-0.77

ournals

-0.71

utenberg

-0.71

ality

-0.70

olls

-0.69

eal

-0.65

iety

-0.64

nexus

-0.63

imedia

-0.62

agonist

-0.62

POSITIVE LOGITS

saf

0.76

 CLSID

0.73

hammad

0.68

WER

0.68

²¾

0.68

liction

0.66

hurst

0.63

ãĥ¯ãĥ³

0.63

ļé

0.61

ABLE

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.