INDEX

Explanations

code-related commands and references in programming contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.43

 trattano

-0.43

 Administrativna

-0.42

 face

-0.42

↵

-0.41

rrggbb

-0.41

//

-0.40

lgari

-0.40

లి

-0.39

seam

-0.39

POSITIVE LOGITS

 Monfieur

0.79

 purpoſe

0.78

 تضيفلها

0.77

]--;

0.75

 cauſe

0.74

PerformLayout

0.73

 ſtate

0.73

 myſelf

0.72

parsedMessage

0.70

 pleaſure

0.70

Activations Density 0.224%

code-related commands and references in programming contexts

No Comments

No Known Activations