INDEX

Explanations

neurodiversity-related terms, specifically related to autism

oai_token-act-pair · gpt-3.5-turbo

references to autism and related conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rons

-0.76

ateur

-0.72

nesday

-0.72

nant

-0.71

pole

-0.66

liam

-0.63

warm

-0.63

maid

-0.61

bare

-0.61

 Paid

-0.61

POSITIVE LOGITS

 spectrum

1.40

 Spectrum

1.23

 diagnoses

0.96

 disorder

0.93

 diagnosis

0.88

 symptoms

0.87

 disorders

0.84

 susceptibility

0.82

 traits

0.82

 autism

0.81

Activations Density 0.040%

neurodiversity-related terms, specifically related to autism

references to autism and related conditions

No Comments

No Known Activations