INDEX

Explanations

terms related to measurements and evaluations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Meksiku

-0.55

FieldNumber

-0.53

zole

-0.44

stateMutability

-0.44

HasBeenSet

-0.43

WithIOException

-0.43

setLayoutManager

-0.42

StructEnd

-0.41

gar

-0.41

ulier

-0.41

POSITIVE LOGITS

})*/

0.81

 Shakspeare

0.81

 AssemblyTitle

0.81

 pleaſure

0.81

τουργ

0.79

 poffible

0.77

MENAFN

0.76

 ſtate

0.76

endpush

0.75

trường

0.73

Activations Density 0.801%

terms related to measurements and evaluations in various contexts

No Comments

No Known Activations