INDEX

Explanations

punctuation and numerical formats

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

academic paper citations

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

 pegatinas

-0.46

Portale

-0.45

Scénario

-0.40

Quiénes

-0.38

 almendras

-0.38

 NavController

-0.37

rboles

-0.37

CppMethod

-0.37

 primaire

-0.37

jamientos

-0.36

POSITIVE LOGITS

 Signalez

0.50

+#+

0.43

 typelib

0.43

 joão

0.43

äsent

0.42

 jspb

0.42

resolvers

0.41

Kra

0.41

EndGlobalSection

0.41

FormTagHelper

0.40

Activations Density 0.031%

punctuation and numerical formats

academic paper citations

No Comments

No Known Activations