INDEX

Explanations

references to membership or affiliations within groups or organizations

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

the word "member" and phrases related to membership.

oai_token-act-pair · gpt-4o Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

醐

-0.81

 Harwood

-0.80

 defaultstate

-0.76

EIS

-0.76

 Normdatei

-0.75

NOI

-0.74

GLY

-0.74

]--;

-0.74

rawQuery

-0.73

 "\""

-0.72

POSITIVE LOGITS

 members

1.62

 member

1.52

members

1.48

 Members

1.46

Members

1.35

 Member

1.33

member

1.31

 MEMBERS

1.27

 MEMBER

1.23

Member

1.21

Activations Density 0.059%

references to membership or affiliations within groups or organizations

the word "member" and phrases related to membership.

No Comments

No Known Activations