INDEX

Explanations

various terms and concepts related to social interactions and contexts

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

followed by "social"

np_acts-logits-general · gemini-2.0-flash

social justice, status, functions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 contemporánea

-0.45

 independientes

-0.45

 Económica

-0.45

 alemanes

-0.43

 Suiza

-0.42

 coronel

-0.42

 recours

-0.42

 alemana

-0.41

 Cientí

-0.41

 imperio

-0.41

POSITIVE LOGITS

 social

2.03

Social

2.03

 Social

2.00

social

1.99

 SOCIAL

1.94

SOCIAL

1.80

 sociale

1.51

 soziale

1.43

 sozialen

1.42

 sociaux

1.40

Activations Density 0.067%

various terms and concepts related to social interactions and contexts

followed by "social"

social justice, status, functions

No Comments

No Known Activations