INDEX

Explanations

terms related to the pathogenesis and pathological processes of diseases

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

pathogenesis and pathophysiology

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StructEnd

-0.63

 '\\;'

-0.57

complexContent

-0.57

 Anſ

-0.55

potranspiration

-0.53

 tartalomajánló

-0.52

GHIJKLM

-0.51

$_"

-0.51

Microkernel

-0.50

providedIn

-0.49

POSITIVE LOGITS

 pathogenesis

0.84

 pathogenic

0.79

opathological

0.74

 patho

0.71

opatho

0.70

 Patho

0.68

patho

0.68

Patho

0.65

opathology

0.64

 pathological

0.60

Activations Density 0.090%

terms related to the pathogenesis and pathological processes of diseases

pathogenesis and pathophysiology

No Comments

No Known Activations