INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

FFER

-0.79

Reviewer

-0.72

ROM

-0.71

icultural

-0.70

Rush

-0.69

HER

-0.67

istical

-0.67

Roberts

-0.67

 abst

-0.65

PART

-0.64

POSITIVE LOGITS

racuse

0.76

 Dres

0.73

 Tate

0.69

FSA

0.67

LS

0.67

dylib

0.66

CSI

0.66

 Baton

0.65

 Dakota

0.65

 Laurel

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.