INDEX

Explanations

instances of the word "delete" in various contexts

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

deleted

-0.62

 Horowitz

-0.60

 amendment

-0.60

İY

-0.59

folgen

-0.58

ixon

-0.57

 Philist

-0.56

 Pemer

-0.56

ällig

-0.56

 deleted

-0.56

POSITIVE LOGITS

delete

1.46

RetentionPolicy

0.91

 ContentValues

0.83

DELETE

0.80

EndInit

0.79

WriteBarrier

0.77

PerformLayout

0.77

rmtree

0.73

yship

0.73

 AssemblyCulture

0.72

Activations Density 0.036%

instances of the word "delete" in various contexts

No Comments

No Known Activations