INDEX

Explanations

references to autism and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to autism and its associated traits or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rons

-0.72

nant

-0.69

 Frey

-0.66

 Cull

-0.65

fare

-0.64

ded

-0.64

 Dull

-0.63

ectar

-0.61

 Paid

-0.60

Doe

-0.60

POSITIVE LOGITS

 spectrum

1.06

 Spectrum

0.97

obic

0.77

 diagnoses

0.74

alysed

0.74

 autism

0.73

 psychosis

0.72

 epile

0.71

 Autism

0.71

auga

0.70

Activations Density 0.017%

references to autism and related terms

terms related to autism and its associated traits or conditions

No Comments

No Known Activations