INDEX

Explanations

technical terms and acronyms, especially related to information technology and data management

oai_token-act-pair · gpt-3.5-turbo

references to technical or operational terminology related to systems and processes

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

ascal

-0.68

 âĢº

-0.67

ovember

-0.66

zip

-0.55

 Corey

-0.53

buquerque

-0.53

AAP

-0.52

Tik

-0.52

 Boone

-0.52

\":

-0.51

POSITIVE LOGITS

)).

0.86

$.

0.70

]).

0.67

}.

0.67

'.

0.67

%.

0.67

'."

0.66

 unworthy

0.66

.[

0.62

worthiness

0.62

Activations Density 1.196%

technical terms and acronyms, especially related to information technology and data management

references to technical or operational terminology related to systems and processes

No Comments

No Known Activations