INDEX

Explanations

terms related to data structures and algorithms

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

ending in "ens", "ence", or "ent"

np_acts-logits-general · gemini-2.0-flash

completion of prefixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

CloseOperation

-0.80

:✨

-0.63

ⓧ

-0.62

లాలు

-0.60

 autorytatywna

-0.56

 jScrollPane

-0.54

EDEFAULT

-0.54

Personendaten

-0.52

 विश्वसनीयता

-0.51

Autoritní

-0.50

POSITIVE LOGITS

ens

1.20

ENS

1.11

en

1.09

en

1.06

EN

1.04

enn

1.01

ენ

1.01

enc

0.97

ener

0.97

enen

0.97

Activations Density 0.481%

terms related to data structures and algorithms

ending in "ens", "ence", or "ent"

completion of prefixes

No Comments

No Known Activations