INDEX

Explanations

specific terms and categories related to environmental contexts and scientific classifications

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

-0.44

MessageWindow

-0.44

 conmigo

-0.43

 يتيمه

-0.43

sonian

-0.42

 duele

-0.41

 comigo

-0.41

 siècles

-0.41

nasium

-0.40

 rêves

-0.40

POSITIVE LOGITS

<bos>

0.57



0.57

CodeAttribute

0.50

Personensuche

0.49

 propOrder

0.46

SourceChecksum

0.45

tagext

0.45

InvalidProtocol

0.43

SequentialGroup

0.43

writeFieldEnd

0.42

Activations Density 0.128%

specific terms and categories related to environmental contexts and scientific classifications

No Comments

No Known Activations