INDEX

Explanations

keywords and terms related to verification and user interactions

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Vidite

-0.56

+#+#

-0.53

 informée

-0.48

Personendaten

-0.47

TypedDataSet

-0.47

richTextPanel

-0.44

PostInfinity

-0.39

tangentMode

-0.38

 hän

-0.37

 emperador

-0.37

POSITIVE LOGITS

PII

0.50

march

0.47

ofire

0.47

gib

0.46

PPI

0.46

 kaynağından

0.45

devamını

0.45

IBI

0.45

CIL

0.45



0.45

Activations Density 0.048%

keywords and terms related to verification and user interactions

No Comments

No Known Activations