INDEX

Explanations

terms related to cancer and its implications

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

"Can", "scan", "cand", "\", "Q", "ml", "deg", "返"

np_acts-logits-general · gemini-2.0-flash

candidosis, scan

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 StatelessWidget

-0.96

endphp

-0.83

 useHistory

-0.74

$_['

-0.72

 AssemblyCulture

-0.71

 Groupe

-0.68

liert

-0.66

TypeDef

-0.64

IVA

-0.63

ThroughAttribute

-0.63

POSITIVE LOGITS

 Canning

0.99

 Candel

0.94

 Canti

0.89

CAN

0.89

 Canucks

0.84

CAND

0.84

canActivate

0.83

 Cans

0.81

 Canary

0.81

 Cand

0.80

Activations Density 0.159%

terms related to cancer and its implications

"Can", "scan", "cand", "\", "Q", "ml", "deg", "返"

candidosis, scan

No Comments

No Known Activations