INDEX

Explanations

mentions of awards and nominations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

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

AutoScaleMode

-0.47

principalColumn

-0.44

fjspx

-0.40

endpush

-0.39

 vertraut

-0.38

 linkovi

-0.37

 autorytatywna

-0.37

WithIOException

-0.35

 maș

-0.35

csname

-0.35

POSITIVE LOGITS

 outstanding

1.20

 excellence

1.14

 exceptional

1.03

outstanding

1.01

Outstanding

1.01

 exemplary

0.98

 Outstanding

0.96

 Excellence

0.92

Excellence

0.90

excellence

0.89

Activations Density 0.168%

mentions of awards and nominations

No Comments

No Known Activations