INDEX

Explanations

URLs and web documentation references

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

APIs, documentation, or help pages

np_acts-logits-general · gemini-2.0-flash

api, wiki, help, docs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

OGND

-0.60

 AssemblyVersion

-0.57

 queſta

-0.55

ectady

-0.47

edith

-0.47

GTCX

-0.46

ressum

-0.46

gonic

-0.46

ennio

-0.45

Havolalar

-0.45

POSITIVE LOGITS

tonode

0.46

errHandler

0.44

0.39

httphttps

0.38

RectangleBorder

0.38

 GoogleFonts

0.36

AppMethodBeat

0.36

 varandra

0.34

createNewFile

0.34

 utafiti

0.33

Activations Density 0.193%

URLs and web documentation references

APIs, documentation, or help pages

api, wiki, help, docs

No Comments

No Known Activations