INDEX

Explanations

terms related to size and measurement in a given context

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

 CanadaChoose

-0.69

´

-0.68

umers

-0.56

 wich

-0.54

ContentLoaded

-0.52

(!)

-0.52

 (...)

-0.51

 garant

-0.49

´)

-0.47

(!)

-0.46

POSITIVE LOGITS

 Monfieur

0.93

 auroit

0.91

 barbati

0.86

 pouvoit

0.83

 étoient

0.82

 feroit

0.82

 Dijo

0.81

 nød

0.80

 vérit

0.80

სქოლიო

0.79

Activations Density 23.735%

terms related to size and measurement in a given context

No Comments

No Known Activations