INDEX

Explanations

specialized terminology and expressions related to technical subjects

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

starting with "ex" or "und"

np_acts-logits-general · gemini-2.0-flash

ex, und, eld prefixes

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

er

-2.97

ER

-1.58

erà

-1.41

erate

-1.39

erii

-1.22

erl

-1.19

erent

-1.12

erai

-1.10

erus

-1.09

erle

-1.09

POSITIVE LOGITS

ERS

0.63

 degradability

0.54

logical

0.54

erex

0.52

ʒ

0.51

hoid

0.51

 paramInt

0.49

bewerken

0.49

erv

0.48

 tartalomajánló

0.48

Activations Density 0.386%

specialized terminology and expressions related to technical subjects

starting with "ex" or "und"

ex, und, eld prefixes

No Comments

No Known Activations