INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

machine

-0.81

boards

-0.75

glers

-0.74

killer

-0.74

cule

-0.71

hov

-0.69

 brill

-0.69

 Clicker

-0.68

renheit

-0.68

paper

-0.65

POSITIVE LOGITS

ospital

0.74

 ribs

0.70

 apolog

0.68

NRS

0.66

MY

0.65

EXT

0.63

bil

0.62

 Annex

0.62

 unborn

0.61

escription

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.