INDEX

Explanations

occurrences of punctuation marks, especially periods, in a code snippet

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

method chaining delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 desmotivaciones

-1.02

transQ

-0.97

$_(

-0.97

 queſta

-0.95

ロウィン

-0.94

 indígen

-0.93

 increí

-0.93

linawan

-0.91

 Verſ

-0.90

majánló

-0.90

POSITIVE LOGITS

0.65

0.47

->

0.43

be

0.43

().

0.43

以

0.41

::

0.41

to

0.40

に

0.40

“

0.39

Activations Density 0.008%

occurrences of punctuation marks, especially periods, in a code snippet

method chaining delimiters

No Comments

No Known Activations