INDEX

Explanations

terms and phrases indicating optionality or non-mandatory elements in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 }}^{\

-0.72

<?,

-0.67

 Reyna

-0.66

ọi

-0.64

endmodule

-0.63

 sonnen

-0.58

Xna

-0.57

Sent

-0.57

OwnProperty

-0.57

</tr>

-0.56

POSITIVE LOGITS

 Optional

1.64

 optional

1.59

optional

1.58

Optional

1.49

 OPTIONAL

1.36

OPTIONAL

1.26

 opcional

1.23

opcional

1.09

 optionally

1.06

 voluntary

1.06

Activations Density 0.110%

terms and phrases indicating optionality or non-mandatory elements in a technical context

No Comments

No Known Activations