INDEX

Explanations

function-related code snippets and object property manipulations

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

Code tokens followed by punctuation

np_acts-logits-general · gemini-2.0-flash

code parsing and syntax

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

}))

-0.66

")"

-0.60

?')

-0.60

})*/

-0.59

]];

-0.59

]')

-0.58

?");

-0.57

</h5>

-0.56

]))

-0.55

;*/

-0.54

POSITIVE LOGITS

".

1.55

'.

1.47

).

1.47

”.

1.42

').

1.41

").

1.40

’.

1.37

“.

1.36

 "").

1.35

].

1.32

Activations Density 0.753%

function-related code snippets and object property manipulations

Code tokens followed by punctuation

code parsing and syntax

No Comments

No Known Activations