INDEX

Explanations

numeric values or measurements

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

Floating point numbers and/or delimiters

np_acts-logits-general · gemini-2.0-flash

numbers and headings

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Билгалдахарш

-0.84

ghijklmnop

-0.71

transQ

-0.69

 desmotivaciones

-0.68

 auffi

-0.67

征詢我

-0.67

ElementException

-0.67

脚注の使い方

-0.67

IntoConstraints

-0.65

gucig

-0.65

POSITIVE LOGITS

0.89

}$.

0.66

|.

0.66

$.

0.60

].

0.59

}.

0.58

.'.

0.58

)}.

0.58

<bos>

0.57

>.

0.57

Activations Density 1.110%

numeric values or measurements

Floating point numbers and/or delimiters

numbers and headings

No Comments

No Known Activations