INDEX

Explanations

keyword-related technical terms and documentation references

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

Code snippets or programming-related terms

np_acts-logits-general · gemini-2.0-flash

builders and code parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

StructEnd

-0.57

 GenerationType

-0.55

 onCreateView

-0.48

íncia

-0.47

onAttach

-0.47

onViewCreated

-0.47

DataBind

-0.45

قليم

-0.45

Demografía

-0.45

glGet

-0.45

POSITIVE LOGITS

 Builder

0.69

 saites

0.65

 builder

0.64

 विश्वसनीयता

0.62

Builder

0.62

ingale

0.59

mazione

0.59

builder

0.58

 builders

0.57

 autorytatywna

0.56

Activations Density 0.217%

keyword-related technical terms and documentation references

Code snippets or programming-related terms

builders and code parameters

No Comments

No Known Activations