INDEX

Explanations

mentions of social media posts or written communication

oai_token-act-pair · gpt-3.5-turbo

references to communication and social media interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Occupations

-0.76

tics

-0.75

 Empires

-0.70

 sexes

-0.66

 Cups

-0.66

 Steps

-0.63

 Buildings

-0.63

ernels

-0.63

 Ones

-0.63

 wards

-0.63

POSITIVE LOGITS

 titled

0.94

 called

0.90

 involving

0.87

 resembling

0.84

 consisting

0.81

 wherein

0.81

 aimed

0.76

 whereby

0.76

assian

0.76

 entitled

0.74

Activations Density 0.547%

mentions of social media posts or written communication

references to communication and social media interactions

No Comments

No Known Activations