INDEX

Explanations

phrases indicating a search for suitable locations or services

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

here to, for ., <start_of_turn> user

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inctions

-0.39

Ecotoxicity

-0.39

+#+#

-0.38

✷

-0.36

 Polsek

-0.36

 lavable

-0.36

‗

-0.36

fpr

-0.36

[]*

-0.35

 gustó

-0.34

POSITIVE LOGITS

rungsseite

0.57

__(/*!

0.52

AddTagHelper

0.52

setVerticalGroup

0.50

verifyException

0.49

AndroidJUnit

0.48

 AssemblyCompany

0.47

 here

0.47

ductory

0.45

 HasFactory

0.45

Activations Density 0.004%

phrases indicating a search for suitable locations or services

here to, for ., <start_of_turn> user

No Comments

No Known Activations