INDEX

Explanations

terms related to specific medical syndromes

oai_token-act-pair · gpt-3.5-turbo

references to various medical syndromes

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

endar

-0.84

yright

-0.83

endars

-0.76

undai

-0.76

nuts

-0.73

ardless

-0.72

umer

-0.66

iances

-0.66

ried

-0.66

tesy

-0.65

POSITIVE LOGITS

 Syndrome

1.02

ptoms

0.84

 syndrome

0.84

 Symptoms

0.78

rosis

0.76

 Spectrum

0.76

ogyn

0.71

 symptoms

0.69

 psychosis

0.68

Osc

0.68

Activations Density 0.012%

terms related to specific medical syndromes

references to various medical syndromes

No Comments

No Known Activations