INDEX

Explanations

references to rows and data organization in tabular formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 majeur

-0.93

*/),

-0.89

))->

-0.88

 virtù

-0.85

}))

-0.84

Anhalt

-0.80

)))

-0.77

ssi

-0.76

}}},

-0.76

 behö

-0.75

POSITIVE LOGITS

Row

1.86

row

1.86

 rows

1.75

Row

1.68

ROW

1.66

row

1.65

 Rows

1.54

rows

1.50

ROW

1.48

Rows

1.42

Activations Density 0.030%

references to rows and data organization in tabular formats

No Comments

No Known Activations