INDEX

Explanations

statements related to the perception and impact of societal norms or beliefs on individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

polation

-0.53

 Synagogue

-0.52

ΠΟ

-0.51

actory

-0.50

 lati

-0.48

adau

-0.47

umbnail

-0.47

AIRS

-0.47

śred

-0.47

ignements

-0.46

POSITIVE LOGITS

rawDesc

0.82

addCriterion

0.79

ThroughAttribute

0.70

 focus

0.70

 mindset

0.66

setVerticalGroup

0.66

uxxxx

0.64

WithIOException

0.63

Personendaten

0.63

 emphasis

0.62

Activations Density 0.327%

statements related to the perception and impact of societal norms or beliefs on individuals

No Comments

No Known Activations