INDEX

Explanations

mentions of medical tests

oai_token-act-pair · gpt-3.5-turbo

references to various medical tests and evaluations

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

ĺħ

-0.79

EngineDebug

-0.72

deals

-0.69

 Leilan

-0.68

theless

-0.66

 Tale

-0.65

Esc

-0.65

future

-0.63

joy

-0.63

TeX

-0.62

POSITIVE LOGITS

osterone

1.34

imony

1.03

 technicians

0.83

 kits

0.82

ysis

0.80

 tests

0.80

udo

0.79

icles

0.77

ifies

0.76

 performed

0.76

Activations Density 0.036%

mentions of medical tests

references to various medical tests and evaluations

No Comments

No Known Activations