INDEX

Explanations

labels and identifiers related to error handling and logging in programming contexts

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

Code or file paths with punctuation

np_acts-logits-general · gemini-2.0-flash

separators in code

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

ьаж

-0.96

]--;

-0.92

 SwitchCompat

-0.92

adaptiveStyles

-0.90

 betweenstory

-0.86

 insuffisamment

-0.85

RegistryLite

-0.80

')):

-0.80

évaluateur

-0.79

)}_{

-0.77

POSITIVE LOGITS

0.60

0.45

merk

0.42

 alimentaria

0.42

くれました

0.42

posição

0.41

 materna

0.41

 boyunca

0.41

 Deletes

0.40

Activations Density 0.148%

labels and identifiers related to error handling and logging in programming contexts

Code or file paths with punctuation

separators in code

No Comments

No Known Activations