INDEX

Explanations

biological terms and entities related to cancer research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 opérateur

-0.70

AutoScaleMode

-0.68

#+#

-0.66

UnsafeEnabled

-0.65

 puissiez

-0.61

UnusedPrivate

-0.59

BagConstraints

-0.59

MLLoader

-0.58

ebaran

-0.56

adaptiveStyles

-0.56

POSITIVE LOGITS

 survi

0.58

 CITED

0.52

izr

0.51

 prohibit

0.51

 cathe

0.49

 InputDecoration

0.48

aqu

0.47

 carbonic

0.46

 involuc

0.46

GroupLayout

0.45

Activations Density 2.300%

biological terms and entities related to cancer research

No Comments

No Known Activations