INDEX

Explanations

data structure attributes or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 practically

-0.36

 برو

-0.34

stringstream

-0.34

 everything

-0.34

 Präsidenten

-0.34

 financial

-0.33

liesslich

-0.33

væ

-0.33

 lean

-0.33

 bậc

-0.33

POSITIVE LOGITS

GEBURTSDATUM

0.82

 resourceCulture

0.76

GraphicsUnit

0.76

 estekak

0.70

parsedMessage

0.65

BufferException

0.64

adaptiveStyles

0.60

 Roskov

0.58

 typelib

0.57

RTSC

0.57

Activations Density 0.162%

data structure attributes or identifiers

No Comments

No Known Activations