INDEX

Explanations

terms related to unity or togetherness

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

 Altogether

-0.57

 together

-0.54

 altogether

-0.47

together

-0.47

 Together

-0.45

ChildScrollView

-0.43

Together

-0.43

 TOGETHER

-0.43

GETHER

-0.39

viewtopic

-0.36

POSITIVE LOGITS

цездатний

0.73

 ujednoznacz

0.62

CppMethod

0.55

 désolés

0.55

 AssemblyCulture

0.54

########.

0.53

AndEndTag

0.53

 صوتيه

0.50

verwijspagina

0.49

 surla

0.48

Activations Density 0.001%

terms related to unity or togetherness

No Comments

No Known Activations