INDEX

Explanations

references to flowcharts and visual representations of processes

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

figures and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AddTagHelper

-0.77

 Chwiliwch

-0.75

 OFDb

-0.69

 queſta

-0.68

writeField

-0.68

 autorytatywna

-0.66

 transfieras

-0.66

 AssemblyCulture

-0.66

GOTREF

-0.66

 ſind

-0.66

POSITIVE LOGITS

↵↵

0.35

<eos>

0.32

 ExecuteAsync

0.31

 infraestructura

0.30

 générations

0.29

 ingenieros

0.29

 incendios

0.29

 fiables

0.29

 escenarios

0.28

 découvertes

0.28

Activations Density 0.104%

references to flowcharts and visual representations of processes

figures and technical terms

No Comments

No Known Activations