INDEX

Explanations

high-ranking positions or titles like "principal," "director," or "owner" in a professional context

oai_token-act-pair · gpt-3.5-turbo

titles and roles related to authority or leadership positions

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

crew

-0.83

CRIP

-0.74

 underlying

-0.64

awed

-0.63

ploy

-0.61

 disparate

-0.61

 docking

-0.60

ename

-0.60

 overhead

-0.59

hr

-0.58

POSITIVE LOGITS

 extraord

0.86

 Theodore

0.83

 Jeffrey

0.82

 laureate

0.82

 Daryl

0.81

 Andrew

0.80

 Shaun

0.78

 Stacy

0.77

 Gina

0.76

 Gerald

0.76

Activations Density 0.337%

high-ranking positions or titles like "principal," "director," or "owner" in a professional context

titles and roles related to authority or leadership positions

No Comments

No Known Activations