INDEX

Explanations

code-related imports in programming documentation

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

import and subsequent code/technical terms

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

Personendaten

-0.66

tonsoft

-0.64

 ſte

-0.60

.*")]

-0.60

 NSCoder

-0.58

oa̍t

-0.55

Jîn

-0.53

 ſol

-0.50

AndEndTag

-0.50

 виправивши

-0.49

POSITIVE LOGITS

CloseOperation

0.44

WebControls

0.41

 enfrentar

0.40

DeleteBehavior

0.40

 Cinem

0.38

CrossRef

0.37

Lähteet

0.36

Références

0.35

 inspecting

0.34

labelText

0.33

Activations Density 0.000%

code-related imports in programming documentation

import and subsequent code/technical terms

No Comments

No Known Activations