INDEX

Explanations

terms related to programming commands and build scripts

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

 instructions

-1.16

 instruction

-1.10

Instructions

-1.09

 Instructions

-1.08

instructions

-1.07

 Instruction

-1.01

 instrucciones

-1.01

 INSTRUCTIONS

-0.99

 istruzioni

-0.96

instruction

-0.95

POSITIVE LOGITS

 CreateTagHelper

0.54

 Réponses

0.42

 Photocase

0.42

pointments

0.41

fördert

0.40

 Quote

0.40

dungen

0.39

 quote

0.39

Nek

0.39

Ned

0.38

Activations Density 0.145%

terms related to programming commands and build scripts

No Comments

No Known Activations