INDEX

Explanations

terms and phrases related to technical specifications and issues with software or hardware

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

-0.51

 összes

-0.50

final

-0.50

ow

-0.48

 Schell

-0.47

-0.46

-0.45

 final

-0.43

pan

-0.42

POSITIVE LOGITS

 myſelf

0.85

 '\\;'

0.85

 Monfieur

0.81

Efq

0.80

 ―――――

0.79

 оригіналу

0.79

 snippetHide

0.79

 Jefus

0.79

 pinulongan

0.78

 Numerade

0.76

Activations Density 10.326%

terms and phrases related to technical specifications and issues with software or hardware

No Comments

No Known Activations