INDEX

Explanations

references to microphones and prototypes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

conf

-0.54

</b>

-0.51

res

-0.46

).

-0.46

-0.42

pr

-0.41

NonNull

-0.40

deka

-0.39

lu

-0.39

POSITIVE LOGITS

DockStyle

1.17

 prototype

1.16

 prototypes

1.12

 Prototype

1.08

 ProtoMessage

0.97

 microphone

0.95

EndProject

0.91

Prototype

0.90

 stove

0.89

mic

0.89

Activations Density 0.077%

references to microphones and prototypes

No Comments

No Known Activations