INDEX

Explanations

specific names and terminologies related to scientific studies and research methodologies

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

starting with "ota" or "ta"

np_acts-logits-general · gemini-2.0-flash

ota, mota, kota

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ExecuteAsync

-0.68

instantiate

-0.58

typeorm

-0.52

สม

-0.52

Tri

-0.52

 statement

-0.52

veil

-0.51

án

-0.51

robin

-0.51

łko

-0.50

POSITIVE LOGITS

ting

0.90

 pleaſure

0.80

 preocupes

0.80

 ſub

0.74

 poffe

0.72

AndEndTag

0.72

 juſt

0.72

IndentedString

0.72

 fubject

0.71

 ſeveral

0.70

Activations Density 0.694%

specific names and terminologies related to scientific studies and research methodologies

starting with "ota" or "ta"

ota, mota, kota

No Comments

No Known Activations