INDEX

Explanations

phrases expressing future intentions or plans

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

time or future occurrences

np_acts-logits-general · gemini-2.0-flash

anytime soon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 متعلقه

-0.49

сього

-0.46

 AssemblyCulture

-0.46

ThroughAttribute

-0.45

 joined

-0.43

RefreshLayout

-0.43

 comuna

-0.42

Produzione

-0.41

 must

-0.40

ồng

-0.39

POSITIVE LOGITS

 anytime

1.15

 foreseeable

1.00

 EVER

0.96

 ever

0.89

 jemals

0.87

 jamás

0.87

 Anytime

0.83

 unless

0.82

unless

0.81

easily

0.79

Activations Density 0.273%

phrases expressing future intentions or plans

time or future occurrences

anytime soon

No Comments

No Known Activations