INDEX

Explanations

words related to medical conditions and their impact on health

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

legal alternative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 TextAppearance

-0.46

udic

-0.46

 Numerade

-0.44

expectation

-0.38

 ادار

-0.38

 FAVOR

-0.38

 للاسماء

-0.38

WireFormatLite

-0.38

uerung

-0.37

dieran

-0.37

POSITIVE LOGITS

 <=",

0.51

tagHelperRunner

0.49

 GenerationType

0.48

aronder

0.42

InputBorder

0.42

 '\\;'

0.42

 teď

0.40

 AssemblyCompany

0.40

awtextra

0.39

jsonwebtoken

0.39

Activations Density 0.140%

words related to medical conditions and their impact on health

legal alternative

No Comments

No Known Activations