INDEX

Explanations

header tags in a document

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

Text after HTML `<h4>` tags

np_acts-logits-general · gemini-2.0-flash

section titles

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

 piú

-0.36

 preghiera

-0.36

 rivista

-0.36

 typelib

-0.35

onAttach

-0.35

úgó

-0.35

IsMutable

-0.35

iyle

-0.34

 Moscú

-0.33

 utafitiHapana

-0.32

POSITIVE LOGITS

<h4>

0.80

<th>

0.63

 getItemId

0.56

 Архів

0.54

setUserId

0.54

Norbert

0.53

 AssemblyTitle

0.52

 Vara

0.51

rup

0.51

Wh

0.50

Activations Density 0.113%

header tags in a document

Text after HTML `<h4>` tags

section titles

No Comments

No Known Activations