INDEX

Explanations

references to polling and surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

çak

-0.57

UserScript

-0.54

 Câmara

-0.53

 szüks

-0.52

 hason

-0.51

tvguidetime

-0.50

 bouche

-0.50

 poussière

-0.49

alva

-0.48

 tegens

-0.48

POSITIVE LOGITS

 poll

1.21

poll

0.94

 Poll

0.94

Poll

0.86

 loop

0.85

 polls

0.81

 POLL

0.78

 Polls

0.76

ga

0.75

 Wonder

0.72

Activations Density 0.060%

references to polling and surveys

No Comments

No Known Activations