INDEX

Explanations

references to medical and biochemical terms, especially involving specific proteins, antibodies, and treatments

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

words starting with i

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

étoit

-0.65

aucune

-0.54

animaux

-0.51

prnewswire

-0.50

œuvres

-0.49

hombres

-0.47

attaque

-0.46

símbolo

-0.46

regler

-0.46

ReusableCell

-0.46

POSITIVE LOGITS

0.68

0.65

0.62

 iVar

0.59

 IUser

0.58

idUser

0.55

 isComment

0.55

iVar

0.54

Ii

0.54

Ica

0.54

Activations Density 0.113%

references to medical and biochemical terms, especially involving specific proteins, antibodies, and treatments

words starting with i

No Comments

No Known Activations

references to medical and biochemical terms, especially involving specific proteins, antibodies, and treatments

words starting with i

No Comments

No Known Activations