INDEX

Explanations

programming-related elements and structures within a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.75

-0.73

-0.71

CH

-0.71

-0.69

-0.68

-0.67

POSITIVE LOGITS

ſelves

1.40

 desmotivaciones

1.30

 itſelf

1.30

ſelf

1.30

 myſelf

1.25

 étoit

1.21

 Italij

1.21

 pleaſure

1.18

 Monfieur

1.17

 ainfi

1.16

Activations Density 1.758%

programming-related elements and structures within a coding context

No Comments

No Known Activations