INDEX

Explanations

technical terms and code-related keywords

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

 AssemblyVersion

-0.51

transQ

-0.50

AnimationsModule

-0.46

HideFlags

-0.45

ViewFeatures

-0.44

numerusform

-0.43

antMatchers

-0.43

 nogen

-0.42

atisk

-0.42

 Normdatei

-0.42

POSITIVE LOGITS

 buffered

0.40

 concre

0.39

 حض

0.39

 snippetHide

0.39

utsal

0.38

 timeType

0.36

medriver

0.36

 "/";

0.36

 hela

0.36

uxxxx

0.35

Activations Density 0.000%

technical terms and code-related keywords

No Comments

No Known Activations