INDEX

Explanations

mentions of disabilities

oai_token-act-pair · gpt-3.5-turbo

terms related to disabilities and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

furt

-0.80

 Collider

-0.78

orically

-0.71

soType

-0.71

 Crowley

-0.70

-0.69

ulate

-0.68

hunt

-0.68

hens

-0.67

gres

-0.67

POSITIVE LOGITS

 disabilities

0.94

 disability

0.91

 impair

0.90

 Disability

0.83

 impairment

0.78

 inval

0.77

 suff

0.77

 diagnoses

0.77

 cripp

0.75

 Disabled

0.75

Activations Density 0.065%

mentions of disabilities

terms related to disabilities and their implications

No Comments

No Known Activations