INDEX

Explanations

phrases indicating the presence or involvement of women in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 purpoſe

-0.94

 pleaſure

-0.89

 juſ

-0.81

 ſever

-0.80

 myſelf

-0.79

 feroit

-0.77

 uſe

-0.77

 ſtate

-0.77

 uſed

-0.75

 ſta

-0.74

POSITIVE LOGITS

1.37

0.69

{~

0.60

own

0.59

𝑠

0.55

ils

0.54

Ys

0.52

etts

0.52

mens

0.52

ds

0.51

Activations Density 0.248%

phrases indicating the presence or involvement of women in various contexts

No Comments

No Known Activations