INDEX

Explanations

Java import statements related to various utility and logging libraries

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

<start_of_turn>user

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

matchCondition

-0.44

Blockly

-0.40

TypedDataSet

-0.35

<eos>

-0.35

StringCopy

-0.33

⅘

-0.32

WriteBarrier

-0.31

stdc

-0.31

Personendaten

-0.31

bewerken

-0.30

POSITIVE LOGITS

 zoude

0.61

 mijne

0.59

 zijne

0.58

 desmotivaciones

0.57

majánló

0.57

 ſeinen

0.56

 CURIAM

0.56

 Geiſt

0.54

citroën

0.54

 Autorizaciones

0.53

Activations Density 0.028%

Java import statements related to various utility and logging libraries

<start_of_turn>user

No Comments

No Known Activations

Java import statements related to various utility and logging libraries

<start_of_turn>user

No Comments

No Known Activations