INDEX

Explanations

instances of names and introductions within text

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

my name is

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

 kasarigan

-0.57

Bioaccumulative

-0.52

Хьажоргаш

-0.49

 autorytatywna

-0.49

soort

-0.47

NameInMap

-0.47

 kohdetta

-0.47

CRR

-0.47

 såsom

-0.47

migrationBuilder

-0.46

POSITIVE LOGITS

ArgsConstructor

0.51

who

0.47

 myself

0.46

AutoField

0.44

AutoScaleMode

0.44

rungsseite

0.42

 name

0.41

 belongs

0.41

 AssemblyTitle

0.40

 responsible

0.39

Activations Density 0.004%

instances of names and introductions within text

my name is

No Comments

No Known Activations