INDEX

Explanations

references to prominent figures and political contexts within discussions of race and history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

GEBURTSDATUM

-0.97

 kasarigan

-0.96

 nakalista

-0.91

 disambiguazione

-0.88

 FetchType

-0.85

Diweddarwch

-0.84

RetentionPolicy

-0.84

OGND

-0.83

 snippetHide

-0.82

ReusableCell

-0.82

POSITIVE LOGITS

0.54

<bos>

0.49

LabelTagHelper

0.47

the

0.44

0.43

0.41

and

0.40

in

0.39

werfen

0.38

Activations Density 0.862%

references to prominent figures and political contexts within discussions of race and history

No Comments

No Known Activations