INDEX

Explanations

demonstrative and punctuation marks that denote relationships and lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

]").

-0.60

vician

-0.54

 hasard

-0.53

and

-0.51

or

-0.51

${

-0.51

UnusedPrivate

-0.48

-0.47

SourceChecksum

-0.47

 समीक्षाओं

-0.46

POSITIVE LOGITS

 SafeMath

0.98

 nakalista

0.86

ঃ

0.84

✨:

0.80

 ujednoznacz

0.78

€“

0.77

:—

0.77

:--

0.73

StructEnd

0.73

 fathoms

0.72

Activations Density 0.593%

demonstrative and punctuation marks that denote relationships and lists

No Comments

No Known Activations