INDEX

Explanations

repeated references to scientific terminology and citations, particularly relating to journals and parameters in mathematical or biological contexts

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

The letter "j" (case-insensitive)

np_acts-logits-general · gemini-2.0-flash

J variable/function/initial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

بوابة

-0.51

AuthProvider

-0.47

IBar

-0.46

 kanssa

-0.44

 rozwój

-0.43

 vzduchu

-0.43

wnątrz

-0.42

Autres

-0.42

abstractmethod

-0.41

POSITIVE LOGITS

 defaultstate

0.91

Juf

0.79

0.76

Jy

0.75

JJ

0.74

0.73

JJ

0.73

Jet

0.71

Jh

0.71

Activations Density 0.832%

repeated references to scientific terminology and citations, particularly relating to journals and parameters in mathematical or biological contexts

The letter "j" (case-insensitive)

J variable/function/initial

No Comments

No Known Activations