INDEX

Explanations

mentions of legal or courtroom-related terms and actions

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

function-related terms

np_acts-logits-general · gemini-2.0-flash

advise or convince

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.96

TagMode

-0.80

rungsseite

-0.79

DockStyle

-0.75

complexContent

-0.72

 himo

-0.71

 Audiodateien

-0.68

Enllaces

-0.67

ритори

-0.67

 समीक्षाओं

-0.66

POSITIVE LOGITS

 واق

0.52

참고

0.45

 desaf

0.44

EFIAPI

0.42

typeorm

0.42

 PyObject

0.41

 tận

0.41



0.40

goe

0.40

antaranya

0.39

Activations Density 2.164%

mentions of legal or courtroom-related terms and actions

function-related terms

advise or convince

No Comments

No Known Activations