INDEX

Explanations

terms related to cancer and dementia research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ExecutionContext

-0.55

นวน

-0.49

bumptech

-0.49

 baptized

-0.49

 Polsek

-0.49

Captor

-0.48

ặt

-0.48

 کد

-0.48

etsen

-0.48

ровке

-0.47

POSITIVE LOGITS

Cure

0.95

 cure

0.89

 cures

0.88

 diagnosis

0.88

 Cure

0.87

 sufferers

0.84

 research

0.81

diagnosis

0.80

Diagnosis

0.80

 survivor

0.80

Activations Density 0.322%

terms related to cancer and dementia research

No Comments

No Known Activations