INDEX

Explanations

references to programming functions and directory paths

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

"Return" or "from" followed by technical terms

np_acts-logits-general · gemini-2.0-flash

return from code structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

########.

-1.07

UserScript

-0.90

 كومونز

-0.85

uxxxx

-0.85

__':

-0.79

StructEnd

-0.78

 Himo

-0.77

 Audiodateien

-0.75

findpost

-0.73

 travaillons

-0.72

POSITIVE LOGITS

 transfieras

0.63

AndroidJUnit

0.60

LikeLike

0.57

tagHelper

0.54

 mergeFrom

0.49

twimg

0.48

dAtA

0.48

ByExample

0.47

 فريبيس

0.44

findOrFail

0.43

Activations Density 0.643%

references to programming functions and directory paths

"Return" or "from" followed by technical terms

return from code structures

No Comments

No Known Activations