INDEX

Explanations

occurrences of various types of function calls or method invocations

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

code structure starting with `(`

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

InjectAttribute

-0.66

)))));

-0.65

 NSError

-0.61

 '*':

-0.56

 '.';

-0.56

parsedMessage

-0.55

 "-";

-0.55

 IndexError

-0.54

 ",";

-0.53

 "}";

-0.53

POSITIVE LOGITS

0.96

(\

0.59

<>(

0.58

$(

0.57

\_(

0.57

__(

0.56

（

0.56

>(

0.56

}(

0.56

0.55

Activations Density 0.158%

occurrences of various types of function calls or method invocations

code structure starting with `(`

No Comments

No Known Activations