INDEX

Explanations

references to specific individuals and their attributes in various contexts

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

COUVER

-0.58

(!__

-0.57

AnchorStyles

-0.53

 snippetHide

-0.50

DateField

-0.49

Cary

-0.48

Demografía

-0.47

)}</

-0.47

ANDRO

-0.47

multirow

-0.47

POSITIVE LOGITS

曖昧さ回避

0.53

rungsseite

0.52

 שוליים

0.50

 Membrane

0.49

poir

0.48

 Hentet

0.47

uts

0.46

afin

0.46

 incomplète

0.46

Personendaten

0.46

Activations Density 0.557%

references to specific individuals and their attributes in various contexts

No Comments

No Known Activations