INDEX

Explanations

forms of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 nahilalakip

-0.81

 Signalez

-0.74

SharedCtor

-0.68

CLUDING

-0.66

kloped

-0.64

entennial

-0.63

ICLE

-0.63

ConstraintMaker

-0.63

клопе

-0.61

ocratic

-0.61

POSITIVE LOGITS

Lähteet

0.56

endpush

0.56

flashdata

0.52

ControllerAdvice

0.52

fromCharCode

0.52

hésitez

0.48

OrNil

0.48

 rispar

0.47

stdarg

0.47

 Beispiele

0.47

Activations Density 0.314%

forms of the word "of."

No Comments

No Known Activations