INDEX

Explanations

terms related to cross-linking in various contexts

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

"cross" followed by another word

np_acts-logits-general · gemini-2.0-flash

cross-compound words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Hochspringen

-0.70



-0.67

execSQL

-0.62

apyrus

-0.56

⤹

-0.53

WindowConstants

-0.52

</thead>

-0.52

paikan

-0.51

brać

-0.51

المناصب

-0.51

POSITIVE LOGITS

hairs

0.76

 sectional

0.72

overs

0.71

AxisAlignment

0.66

breed

0.65

hatch

0.65

hair

0.64

 section

0.61

dresser

0.60

roads

0.60

Activations Density 0.099%

terms related to cross-linking in various contexts

"cross" followed by another word

cross-compound words

No Comments

No Known Activations