INDEX

Explanations

references to medical and scientific terms related to conditions and diseases

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

Text after certain punctuation (, . or ...)

np_acts-logits-general · gemini-2.0-flash

legal citations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

期刊论文

-0.55

glEnd

-0.50

QUIR

-0.48

 समीक्षक

-0.48

ASX

-0.46

KRA

-0.45

cx

-0.44

entar

-0.44

PhysRev

-0.43

 encou

-0.43

POSITIVE LOGITS

featureID

0.74

EDEFAULT

0.67

 nakalista

0.63

Források

0.63

 propOrder

0.58

 ComVisible

0.53

Jegyzetek

0.53

endforeach

0.52

 gynhyrchwyd

0.52

ang

0.52

Activations Density 0.188%

references to medical and scientific terms related to conditions and diseases

Text after certain punctuation (, . or ...)

legal citations

No Comments

No Known Activations