INDEX

Explanations

the usage of the term 'self' in class definitions and methods

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

]--;

-0.88

Étienne

-0.60

zmir

-0.60

는

-0.59

oustic

-0.57

Portale

-0.57

doom

-0.57

 pinulongan

-0.56

),

-0.56

cdi

-0.56

POSITIVE LOGITS

self

2.50

selves

1.52

SELF

1.28

 ourselves

1.18

 yourself

1.12

 herself

1.11

Self

1.09

 selves

1.03

ſelf

1.02

 Himself

1.01

Activations Density 0.027%

the usage of the term 'self' in class definitions and methods

No Comments

No Known Activations