INDEX

Explanations

medical treatments or procedures

oai_token-act-pair · gpt-3.5-turbo

references to medical treatments and their effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 compr

-0.69

prints

-0.65

inet

-0.64

arrass

-0.64

erd

-0.64

 frying

-0.63

bour

-0.63

old

-0.60

 nesting

-0.60

uld

-0.60

POSITIVE LOGITS

ilitating

0.87

 treatment

0.87

culosis

0.85

 treatments

0.85

ttes

0.85

 regimen

0.84

 therapies

0.83

 Treatment

0.80

 therapy

0.77

treatment

0.77

Activations Density 0.025%

medical treatments or procedures

references to medical treatments and their effectiveness

No Comments

No Known Activations