INDEX

Explanations

terms related to systems and measurements

oai_token-act-pair · gpt-3.5-turbo

terminology related to systems and their governance or management structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

lees

-0.73

uary

-0.63

 cele

-0.61

aretz

-0.61

zzy

-0.61

abase

-0.60

 Rebell

-0.60

undreds

-0.59

cade

-0.59

yy

-0.59

POSITIVE LOGITS

 interfaces

0.80

 interconnected

0.72

 Powered

0.71

 functioning

0.68

å£«

0.67

 architectures

0.66

 operated

0.66

 subsystem

0.65

chemy

0.65

 detects

0.63

Activations Density 0.688%

terms related to systems and measurements

terminology related to systems and their governance or management structures

No Comments

No Known Activations