INDEX

Explanations

structured data or blocks of code that are associated with commands or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ***!

-0.67

—

-0.65

[](

-0.61

NOPQRST

-0.59

Nen

-0.59

jsxFileName

-0.59

---|---|

-0.58

__':

-0.58

참고

-0.57

########.

-0.57

POSITIVE LOGITS

0.56

0.54

};

0.53

});

0.53

0.51

);

0.49

},

0.49

})

0.49

0.48

Activations Density 0.269%

structured data or blocks of code that are associated with commands or definitions

No Comments

No Known Activations