INDEX

Explanations

references to specific individuals and their associated work related to academic or professional contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Gib

-0.78

 Kemp

-0.71

ή

-0.69

จำ

-0.66

<blockquote>

-0.66

 Nilsson

-0.65

Unchecked

-0.63

XXXXXXXX

-0.63

ي

-0.63

 Ferdinand

-0.62

POSITIVE LOGITS

 للاسماء

1.05

=$?

1.00

[`

0.98

'`

0.95

contentLoaded

0.92

uría

0.92

]`

0.91

),'

0.91

 entanto

0.90

)')

0.89

Activations Density 2.787%

references to specific individuals and their associated work related to academic or professional contributions

No Comments

No Known Activations