INDEX

Explanations

numerical data and formatting related to scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

</thead>

-0.96

OGND

-0.92

]")]

-0.85

__*/

-0.83

PerformLayout

-0.80

PreferredItem

-0.76

SequentialGroup

-0.75

 Roskov

-0.74

XmlAccessType

-0.71

клопе

-0.69

POSITIVE LOGITS

 realistically

0.47

 Siempre

0.47

 impeach

0.45

always

0.45

 twain

0.45

总之

0.44

never

0.44

 always

0.42

 never

0.41

siempre

0.41

Activations Density 0.533%

numerical data and formatting related to scientific or technical contexts

No Comments

No Known Activations