INDEX

Explanations

terms related to potential or possible outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ReusableCell

-0.64

 élevées

-0.52

 bianchi

-0.48

Same

-0.47

aktery

-0.47

 specchio

-0.47

 parcourir

-0.46

 APPEALS

-0.46

lance

-0.46

 contrario

-0.46

POSITIVE LOGITS

 potential

1.78

 Potential

1.64

potential

1.63

Potential

1.63

 possible

1.55

Possible

1.53

 Possible

1.48

possible

1.48

 POTENTIAL

1.48

 POSSIBLE

1.41

Activations Density 0.469%

terms related to potential or possible outcomes

No Comments

No Known Activations