INDEX

Explanations

terms related to cancer treatments and their mechanisms

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

after bracketed numbers

np_acts-logits-general · gemini-2.0-flash

associated function or antigen

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

tagHelperRunner

-0.57

 betweenstory

-0.54

حياته

-0.50

ArgumentParser

-0.50

MENAFN

-0.48

 Jedes

-0.47

 OMITBAD

-0.47

Ligações

-0.46

حياتها

-0.42

writeFieldEnd

-0.42

POSITIVE LOGITS

0.57

 camiset

0.54

axel

0.51

 TMPro

0.50

onomía

0.50

 AssemblyCulture

0.49

TJ

0.48

 IFTT

0.47

bleau

0.47

XmlType

0.46

Activations Density 1.612%

terms related to cancer treatments and their mechanisms

after bracketed numbers

associated function or antigen

No Comments

No Known Activations