INDEX

Explanations

references to technical components or elements in a software context

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

Follows "menu" or "<start_of_turn>" tokens

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

:][

-0.38

aarrggbb

-0.36

zaj

-0.35

SceneManagement

-0.35

 Success

-0.32

haften

-0.32

 success

-0.31

ומת

-0.31

 liquide

-0.30

wohn

-0.30

POSITIVE LOGITS

 Tools

0.66

 Tool

0.62

 File

0.62

 toolbar

0.59

GTCX

0.57

 Command

0.57

 JMenuItem

0.57

Diweddarwch

0.57

Tools

0.57

tool

0.57

Activations Density 0.167%

references to technical components or elements in a software context

Follows "menu" or "<start_of_turn>" tokens

No Comments

No Known Activations