INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

cific

-0.75

alog

-0.66

 Mania

-0.66

sson

-0.64

 Macro

-0.62

 Trap

-0.62

 Blueprint

-0.61

 wander

-0.61

enegger

-0.61

ONSORED

-0.61

POSITIVE LOGITS

abama

0.76

 baker

0.71

Frameworks

0.68

minimum

0.67

ess

0.66

college

0.65

clinton

0.65

 bare

0.63

iper

0.62

parse

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.