INDEX

Explanations

medical treatments or interventions

oai_token-act-pair · gpt-3.5-turbo

references to medical treatments

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

bour

-0.65

ede

-0.65

arrass

-0.64

 compr

-0.63

erd

-0.62

Dick

-0.62

beck

-0.60

inet

-0.60

uld

-0.60

prints

-0.59

POSITIVE LOGITS

 regimen

0.95

 treatments

0.90

 treatment

0.88

 therapies

0.87

ilitating

0.86

 therapy

0.85

 Treatment

0.80

treatment

0.80

ttes

0.78

culosis

0.78

Activations Density 0.025%

medical treatments or interventions

references to medical treatments

No Comments

No Known Activations