INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

eth

-0.67

 Sale

-0.66

tained

-0.63

 Berkeley

-0.63

chev

-0.63

 Sinai

-0.62

onte

-0.60

wal

-0.59

acs

-0.59

tin

-0.59

POSITIVE LOGITS

miah

0.76

HAEL

0.74

rentices

0.72

ouble

0.69

hess

0.68

ensional

0.68

idable

0.67

Position

0.66

utenant

0.66

cussion

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.