INDEX

Explanations

programming constructs related to functions and their parameters

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 @ 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

</i>

-0.59

-0.49

</em>

-0.47

</code>

-0.47

</h3>

-0.44

↵

-0.43

</blockquote>

-0.39

</b>

-0.39

</h4>

-0.38

</u>

-0.36

POSITIVE LOGITS

setVerticalGroup

1.11

expandindo

1.10

SharedCtor

0.93

parsedMessage

0.91

 disambiguazione

0.87

SharedDtor

0.84

 kaarangay

0.81

Personensuche

0.81

 HasFactory

0.78

 &___

0.76

Activations Density 0.044%

programming constructs related to functions and their parameters

<start_of_turn>user

No Comments

No Known Activations