INDEX

Explanations

mentions of the name "Sher" and related context

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Corbin

-0.76

Pars

-0.71

 Pars

-0.69

Mull

-0.69

 Clements

-0.66

 Brooks

-0.64

 Mull

-0.62

 Hicks

-0.61

\},

-0.60

CST

-0.60

POSITIVE LOGITS

 Warhol

1.12

 peruana

1.07

 sherpa

1.05

]")]

0.98

 VIAF

0.96

Peru

0.93

 vectorielles

0.93

Geplaatst

0.93

 Sher

0.93

 Burk

0.92

Activations Density 0.028%

mentions of the name "Sher" and related context

No Comments

No Known Activations