INDEX

Explanations

programming concepts related to data structures and functions

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

DLM properties or attributes

np_acts-logits-general · gemini-2.0-flash

DLM Lens type definitions

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

Према

-0.69

󠁥

-0.59

Bronnen

-0.55

 Blackman

-0.52

ů

-0.49

 Stoll

-0.48

 JADX

-0.48

amica

-0.47

Op

-0.46

EditPart

-0.46

POSITIVE LOGITS

 Scots

1.04

 Scottish

1.04

 Scotland

1.02

Scotland

0.98

 scottish

0.98

Scottish

0.97

 Glasgow

0.91

Glasgow

0.88

 Edinburgh

0.82

Aberdeen

0.80

Activations Density 0.488%

programming concepts related to data structures and functions

DLM properties or attributes

DLM Lens type definitions

No Comments

No Known Activations