INDEX

Explanations

phrases indicating proximity or location

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

location prepositions followed by names

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

 nakalista

-0.39

SupportActionBar

-0.38

ptonshire

-0.35

ordnet

-0.35

enment

-0.35

 invokingState

-0.33

 noten

-0.33

Identyfik

-0.33

balleur

-0.33

 HasFactory

-0.33

POSITIVE LOGITS

KommentareTeilen

0.48

Hozzáférés

0.48

Mui

0.47

uldade

0.46

AnchorStyles

0.46

UVWXYZ

0.45

roga

0.44

zeitig

0.44

PRNewswire

0.44

 htmlFor

0.43

Activations Density 0.002%

phrases indicating proximity or location

location prepositions followed by names

No Comments

No Known Activations