INDEX

Explanations

names of individuals

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

First names

np_acts-logits-general · gemini-2.0-flash

female given names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

migrationBuilder

-0.70

 Meksiku

-0.65

 فريبيس

-0.64

webElementXpaths

-0.63

 ""],

-0.63

ArrowToggle

-0.63

ScopeManager

-0.63

MethodManager

-0.61

IsMutable

-0.61

AnchorStyles

-0.56

POSITIVE LOGITS

Ann

1.00

 Marie

0.94

Ann

0.90

ann

0.89

Rae

0.88

 Anne

0.87

Sue

0.85

 Lynn

0.85

 Jean

0.85

 Leigh

0.84

Activations Density 0.161%

names of individuals

First names

female given names

No Comments

No Known Activations