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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

product

-0.74

abul

-0.74

ugu

-0.71

 Rolling

-0.70

ound

-0.70

obo

-0.69

Magazine

-0.69

poon

-0.69

Lower

-0.68

BUR

-0.68

POSITIVE LOGITS

 contested

0.76

zbollah

0.75

 contrace

0.74

ETF

0.70

 trusts

0.69

 Rohing

0.67

 bets

0.67

 rode

0.66

 trust

0.66

 babys

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.