INDEX

Explanations

references to the name "Adam"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Newberry

-0.78

 onCancelled

-0.76

 Deane

-0.75

Rüyada

-0.74

 kanyang

-0.68

 Mayfield

-0.66

 pinulongan

-0.66

 Laver

-0.65

Tuy

-0.65

/*:

-0.64

POSITIVE LOGITS

 Adam

2.65

Adam

2.45

 adam

1.87

 ADAM

1.70

 Adams

1.58

ADAM

1.53

adam

1.40

Adams

1.31

 adams

1.30

 ADAMS

1.09

Activations Density 0.015%

references to the name "Adam"

No Comments

No Known Activations