INDEX

Explanations

code-related terminology and syntax structures

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\"");

-0.89

{}\

-0.89

 Majefty

-0.88

 Monfieur

-0.83

 whoſe

-0.83

 Theſe

-0.82

 preſent

-0.81

 poffe

-0.81

 deſt

-0.80

 myſelf

-0.80

POSITIVE LOGITS

 codes

1.68

 code

1.66

 Codes

1.66

 Code

1.65

 CODE

1.64

code

1.63

CODE

1.61

codes

1.50

setCode

1.49

Code

1.46

Activations Density 0.110%

code-related terminology and syntax structures

No Comments

No Known Activations