INDEX

Explanations

phrases related to research findings or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 since

-0.73

since

-0.66

 lately

-0.64

 Lately

-0.63

 seit

-0.59

これまで

-0.59

 Since

-0.59

Seit

-0.57

Since

-0.56

toMatchSnapshot

-0.55

POSITIVE LOGITS

########.

0.71

awtextra

0.70

]")]

0.68

providedIn

0.68

RegressionTest

0.67

ⓧ

0.65

 mourut

0.65



0.65

 &___

0.64

AnchorStyles

0.63

Activations Density 0.419%

phrases related to research findings or evidence

No Comments

No Known Activations