INDEX

Explanations

code snippets and definitions related to API requests in programming languages

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

return this

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

EDEFAULT

-0.56

tagHelperRunner

-0.52

 propOrder

-0.49

 AspNetCore

-0.49

itattu

-0.47

PreferredItem

-0.46

cyklopedia

-0.46

posób

-0.46

 actionMode

-0.44

atecas

-0.44

POSITIVE LOGITS

 herself

0.71

 himself

0.63

 yourself

0.63

 itself

0.62

itself

0.60

 themselves

0.59

SELF

0.57

 oneself

0.57

himself

0.56

self

0.56

Activations Density 0.009%

code snippets and definitions related to API requests in programming languages

return this

No Comments

No Known Activations