INDEX

Explanations

references to the subject "She" or related pronouns and possessives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 елның

-0.57

 Judo

-0.52

 Yogi

-0.49

[]=

-0.49

senic

-0.48

setDefault

-0.48

 handker

-0.48

 Foul

-0.48

igo

-0.48

जा

-0.48

POSITIVE LOGITS

She

1.84

she

1.80

She

1.76

she

1.72

 herself

1.25

 ella

1.22

 Она

1.21

SHE

1.20

她

1.19

Она

1.16

Activations Density 0.207%

references to the subject "She" or related pronouns and possessives

No Comments

No Known Activations