INDEX

Explanations

words related to medical test results

oai_token-act-pair · gpt-3.5-turbo

references to drug test results and their outcomes

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

Nap

-0.84

TOR

-0.79

erity

-0.79

pread

-0.78

emonic

-0.78

chair

-0.75

RAW

-0.74

hare

-0.73

workshop

-0.71

conservancy

-0.70

POSITIVE LOGITS

 positive

0.72

 leukemia

0.71

ATF

0.71

 uranium

0.71

 screening

0.69

 tuberculosis

0.68

 urine

0.68

 unfit

0.68

negative

0.65

 MDMA

0.65

Activations Density 0.038%

words related to medical test results

references to drug test results and their outcomes

No Comments

No Known Activations