INDEX

Explanations

algorithm-related syntax and structures in code providing GPU architecture details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

').

-0.73

')).

-0.72

'),

-0.72

])).

-0.71

']);

-0.69

']).

-0.66

)',

-0.66

")).

-0.65

]).

-0.65

!',

-0.65

POSITIVE LOGITS

1.00

0.78

printf

0.66

std

0.66

std

0.64

 printf

0.63

//#

0.62

.#

0.61

\#

0.60

(#

0.59

Activations Density 0.086%

algorithm-related syntax and structures in code providing GPU architecture details

No Comments

No Known Activations