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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Presence

-0.79

âĸĪ

-0.66

MSN

-0.63

 scrape

-0.63

Malley

-0.63

 Bene

-0.63

 compose

-0.63

 placebo

-0.62

 Onion

-0.62

acebook

-0.61

POSITIVE LOGITS

acious

0.78

opter

0.76

ower

0.69

mad

0.66

Nik

0.66

rab

0.66

igmat

0.66

orce

0.63

araoh

0.63

rod

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.