INDEX

Explanations

words and phrases associated with forms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

IVEREF

-0.75

aarrggbb

-0.74

󠁢

-0.69

RenderAtEndOf

-0.62

ModelSerializer

-0.62

λλην

-0.60

tonode

-0.59

eadilan

-0.59

Espèce

-0.57

__.__

-0.56

POSITIVE LOGITS

Personensuche

0.77

 autorytatywna

0.62

complexContent

0.60

extAlignment

0.58

 كومونز

0.53

ècie

0.51

 hồn

0.49

Portail

0.49

 Koop

0.48

 Krank

0.45

Activations Density 0.049%

words and phrases associated with forms and structures

No Comments

No Known Activations