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

NPR

-0.68

Correct

-0.65

UES

-0.65

Wire

-0.65

 Orth

-0.64

ocene

-0.64

PLIED

-0.64

entimes

-0.64

Journal

-0.62

nat

-0.62

POSITIVE LOGITS

 concess

0.71

otics

0.69

ilee

0.68

monds

0.68

 passively

0.67

++++++++

0.66

ruff

0.64

udeau

0.63

rek

0.63

undai

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.