INDEX

Explanations

symbols and formatting elements often used in data representation or coding contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 intervención

-0.42

 amenazas

-0.40

 sorpresas

-0.39

 explosión

-0.38

 wykonania

-0.37

 candidatura

-0.37

 licencias

-0.36

 exposiciones

-0.36

 discapacidad

-0.35

 posteriormente

-0.35

POSITIVE LOGITS



0.71

ftagPool

0.68

ۜ

0.61

 nakalista

0.61

 ſind

0.60

<unused52>

0.60

addCriterion

0.60

<unused8>

0.60

<pad>

0.60

[@BOS@]

0.60

Activations Density 0.001%

symbols and formatting elements often used in data representation or coding contexts

No Comments

No Known Activations

symbols and formatting elements often used in data representation or coding contexts

No Comments

No Known Activations