INDEX

Explanations

references to file sizes and data storage measurements

oai_token-act-pair · gpt-3.5-turbo

references to memory storage sizes and capacities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

ean

-0.75

zona

-0.71

 abdom

-0.70

eers

-0.68

eve

-0.66

ey

-0.65

yers

-0.64

 evolving

-0.62

places

-0.61

facing

-0.61

POSITIVE LOGITS

MB

0.81

ilit

0.81

ilitation

0.81

TI

0.80

Ts

0.78

BS

0.77

BM

0.77

ata

0.76

isk

0.75

utable

0.75

Activations Density 0.003%

references to file sizes and data storage measurements

references to memory storage sizes and capacities

No Comments

No Known Activations