INDEX

Explanations

mathematical notation and symbols commonly used in formal proofs or algorithms

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

previous terms in sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Бахар

-0.58

CodeAttribute

-0.55

 linkovi

-0.47

뀜

-0.45

Remaining

-0.45

뀐

-0.44

듦

-0.43

 căr

-0.43

 anledning

-0.43

 vuelto

-0.43

POSITIVE LOGITS

 prior

0.56

 previous

0.54

 preceding

0.54

queryInterface

0.47

 Prior

0.42

 PRIOR

0.42

 earlier

0.42

 before

0.40

GenerationType

0.39

prior

0.38

Activations Density 0.028%

mathematical notation and symbols commonly used in formal proofs or algorithms

previous terms in sequences

No Comments

No Known Activations