INDEX

Explanations

mentions of types, categories, and classifications within various contexts

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

questions and answers

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

SequentialGroup

-0.61

 poffible

-0.59

<unused43>

-0.57

<unused41>

-0.57

<unused3>

-0.57

<unused42>

-0.57

<unused51>

-0.57

<unused8>

-0.56

[@BOS@]

-0.56

<pad>

-0.56

POSITIVE LOGITS

you

0.49

he

0.44

 they

0.43

it

0.41

ass

0.40

pa

0.38

we

0.38

you

0.38

0.37

 للاسماء

0.37

Activations Density 0.018%

mentions of types, categories, and classifications within various contexts

questions and answers

No Comments

No Known Activations