INDEX

Explanations

patterns or sequences in data, possibly related to structure or formatting

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

following continuation marks

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

OGND

-0.81

Autoritní

-0.73

UserScript

-0.73

 للاسماء

-0.72

 nonUne

-0.69

 tartalomajánló

-0.68

 pleaſure

-0.67

 purpoſe

-0.66

KURZBESCHREIBUNG

-0.65

ंदीखरीदारी

-0.64

POSITIVE LOGITS

esterno

0.36

 εκ

0.36

Ne

0.36

 Denken

0.35

 contemporánea

0.35

Mutex

0.34

 again

0.34

 onder

0.34

 contemporaine

0.33

сно

0.33

Activations Density 0.010%

patterns or sequences in data, possibly related to structure or formatting

following continuation marks

No Comments

No Known Activations