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

 contribution

-0.67

 paternity

-0.66

ukemia

-0.65

ynamic

-0.64

iterator

-0.62

atical

-0.62

rans

-0.61

cro

-0.60

aird

-0.59

ikuman

-0.59

POSITIVE LOGITS

 Emin

0.88

Anonymous

0.75

Rog

0.73

Ago

0.72

 Gunn

0.72

netflix

0.68

Tea

0.67

Jenn

0.66

 adolesc

0.66

VR

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.