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

mbuds

-0.95

ote

-0.77

vernment

-0.72

theless

-0.71

pex

-0.69

lyak

-0.69

idable

-0.68

utic

-0.68

afort

-0.68

inces

-0.66

POSITIVE LOGITS

Jah

0.68

Ble

0.66

redd

0.66

 Hilbert

0.62

uits

0.61

 retard

0.59

iner

0.58

saf

0.58

 zones

0.58

Lay

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.