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

toggle

-0.76

pixel

-0.67

til

-0.67

lift

-0.67

ombo

-0.66

LinkedIn

-0.66

sie

-0.65

Thumbnail

-0.65

edIn

-0.64

vec

-0.63

POSITIVE LOGITS

QC

0.70

 Dates

0.65

illon

0.64

LIC

0.63

 Dealer

0.62

 buds

0.61

ods

0.61

ewater

0.61

anners

0.61

bernatorial

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.