INDEX

Explanations

occurrences of the asterisk character used for documentation or code annotations

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

/** * `"` and code comments

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵

-0.55

-0.47

↵↵↵↵

-0.45

basicConfig

-0.44

 Paglinawan

-0.44

↵↵↵

-0.44

 препратки

-0.42

<eos>

-0.42

 ModelExpression

-0.42

↵↵↵↵↵↵↵

-0.41

POSITIVE LOGITS

 Houſe

0.53

Diweddarwch

0.53

SBATCH

0.52

 '/':

0.49

"":

0.47

/**

0.47

 }^{*}$

0.46

":

0.46

bibfield

0.46

CompleteListener

0.46

Activations Density 0.005%

occurrences of the asterisk character used for documentation or code annotations

/** * `"` and code comments

No Comments

No Known Activations