INDEX

Explanations

terms related to planning, setting goals, and relational dynamics in various contexts

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

ending in "-ing" followed by punctuation

np_acts-logits-general · gemini-2.0-flash

processes forming nouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 שוליים

-0.63

 OFDb

-0.49

ParallelGroup

-0.46

 EconPapers

-0.46

quelize

-0.45

Asts

-0.44

abestanden

-0.44

helia

-0.44

-------

-0.43

nezeu

-0.43

POSITIVE LOGITS

 púrpura

0.41

 Brasileiro

0.38

fseek

0.37

 bezpeč

0.37

 chapéu

0.37

UrlResolution

0.36

HttpPut

0.35

 gostar

0.35

➊

0.35

 fizer

0.34

Activations Density 1.414%

terms related to planning, setting goals, and relational dynamics in various contexts

ending in "-ing" followed by punctuation

processes forming nouns

No Comments

No Known Activations