INDEX

Explanations

mentions of sons

oai_token-act-pair · gpt-3.5-turbo

mentions of "sons" 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 @ 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

Medic

-0.68

AU

-0.66

HHS

-0.65

Dub

-0.65

patient

-0.65

CDC

-0.65

pmwiki

-0.63

 Nurse

-0.62

 paramed

-0.62

de

-0.61

POSITIVE LOGITS

hip

1.17

 sons

0.99

hips

0.98

ongs

0.97

pins

0.94

terday

0.89

thood

0.89

ieve

0.87

 daughters

0.85

lings

0.84

Activations Density 0.015%

mentions of sons

mentions of "sons" in various contexts

No Comments

No Known Activations