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

steen

-0.77

boss

-0.72

ibo

-0.70

oser

-0.69

eric

-0.68

bow

-0.68

thood

-0.67

eme

-0.67

isoft

-0.66

 Malone

-0.65

POSITIVE LOGITS

 glim

0.75

NetMessage

0.70

 acad

0.69

 glances

0.66

 levers

0.65

 citiz

0.65

liter

0.64

 chairs

0.63

 magazines

0.63

 territ

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.