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

 Sakuya

-0.76

haps

-0.75

Kus

-0.73

-+-+-+-+

-0.71

 Yamato

-0.71

ã

-0.70

amina

-0.69

cius

-0.69

uly

-0.69

 orbs

-0.68

POSITIVE LOGITS

REP

0.74

den

0.66

 orientation

0.66

gen

0.62

 PARK

0.61

jer

0.61

JSON

0.60

 Establishment

0.60

ilitation

0.60

actory

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.