INDEX

Explanations

technical terms and phrases related to restrictions, limits, and regulations

oai_token-act-pair · gpt-3.5-turbo

questions related to limitations and exclusions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Lopez

-0.58

 Rafael

-0.58

Lon

-0.57

 Pound

-0.57

 Barrett

-0.56

 Adolf

-0.56

 Sharif

-0.56

 Sidney

-0.55

 Elvis

-0.54

Pin

-0.54

POSITIVE LOGITS

 oneself

0.82

rawdownloadcloneembedreportprint

0.82

 comprom

0.80

 outweigh

0.78

effic

0.78

.</

0.77

 detriment

0.76

.","

0.75

 compromises

0.74

 stakeholders

0.74

Activations Density 0.912%

technical terms and phrases related to restrictions, limits, and regulations

questions related to limitations and exclusions in various contexts

No Comments

No Known Activations