INDEX

Explanations

references to categories and notes in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

HtmlAttribute

-0.93

tvguidetime

-0.89

AlterField

-0.88

saraba

-0.82

 insuffisamment

-0.79

+#+

-0.77

SOUNDBITE

-0.77

]")]

-0.77

RTLR

-0.75

الدراسه

-0.74

POSITIVE LOGITS

<eos>

1.41

 Wikiseite

0.56

0.52

 wikipagina

0.51

©

0.49

Copyright

0.49

References

0.47

Source

0.47

 beginnetje

0.46

 fonte

0.46

Activations Density 0.579%

references to categories and notes in a document

No Comments

No Known Activations