INDEX

Explanations

terms related to autonomy and personal identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 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

liyor

-0.44

ţion

-0.43

 straightened

-0.42

 הער

-0.42

HStack

-0.41

 workflow

-0.40

idados

-0.39

iſh

-0.39

 zestawie

-0.39

しき

-0.39

POSITIVE LOGITS

 lastName

0.68

 minority

0.63

[*]

0.62

Marker

0.58

 surname

0.57

 Minority

0.57

 overlapping

0.56

 diaspora

0.56

 Marker

0.56

Surname

0.56

Activations Density 1.110%

terms related to autonomy and personal identity

No Comments

No Known Activations