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

ouble

-0.68

hap

-0.66

âĶĢ

-0.66

$.

-0.65

 reconciliation

-0.65

aces

-0.64

bow

-0.63

 tune

-0.63

score

-0.63

Metal

-0.62

POSITIVE LOGITS

idon

0.71

erity

0.67

washer

0.67

 CARD

0.66

milo

0.65

UA

0.64

pload

0.64

 Drac

0.64

zynski

0.63

anyon

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.