INDEX

Explanations

references to autism and discussions related to autism

oai_token-act-pair · gpt-3.5-turbo

terms related to autism and autistic traits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

nant

-0.71

rons

-0.71

Jet

-0.69

 Frey

-0.63

 Dull

-0.62

fare

-0.62

NRS

-0.62

 footsteps

-0.61

 Cull

-0.61

risome

-0.61

POSITIVE LOGITS

 spectrum

1.12

 Spectrum

1.03

nesota

0.78

clair

0.78

obic

0.76

 autism

0.75

auga

0.73

omal

0.72

 diagnoses

0.72

umn

0.71

Activations Density 0.015%

references to autism and discussions related to autism

terms related to autism and autistic traits

No Comments

No Known Activations