INDEX

Explanations

technical terms related to medical procedures and devices

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

preceding tools or instruments

np_acts-logits-general · gemini-2.0-flash

types of tools

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

viewDid

-0.59

arXiv

-0.56

 curtains

-0.54

λώ

-0.54

 beds

-0.52

 occupancy

-0.50

 Occupancy

-0.50

GroupLayout

-0.50

 credits

-0.49

 Plains

-0.49

POSITIVE LOGITS

 tool

0.84

 Tool

0.80

 Tools

0.78

Tool

0.77

 tools

0.76

 chuyên

0.74

tool

0.73

tools

0.72

Tools

0.71

ramienta

0.70

Activations Density 0.354%

technical terms related to medical procedures and devices

preceding tools or instruments

types of tools

No Comments

No Known Activations