INDEX

Explanations

proper nouns, specifically names and surnames

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

names of people and places

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

AccessorTable

-0.46

ThroughAttribute

-0.40

 beginnetje

-0.36

ScopeManager

-0.36

\{\\

-0.35

észetes

-0.35

 naturel

-0.35

 aktual

-0.33

MessageTagHelper

-0.33

URLException

-0.32

POSITIVE LOGITS

batore

0.64

inWeight

0.56

AFR

0.54

 postwar

0.53

 surla

0.52

tvguidetime

0.51

 ſont

0.50

Gön

0.50

$_(

0.50

참고

0.50

Activations Density 0.103%

proper nouns, specifically names and surnames

names of people and places

No Comments

No Known Activations