INDEX

Explanations

phrases indicating statistical significance or results in research contexts

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

academic and scientific writing

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 flushed

-0.57

 aanges

-0.49

Rhestr

-0.49

 Samb

-0.47

 surfaced

-0.46

 Pals

-0.46

intios

-0.46

 üzere

-0.45

 sprouts

-0.44

laught

-0.44

POSITIVE LOGITS

 enfans

0.48

 pleaſure

0.46

canestro

0.45

 ſch

0.42

 Monfieur

0.42

XmlAccessorType

0.41

 ſche

0.41

ientras

0.41

 ſever

0.41

 étoit

0.40

Activations Density 0.659%

phrases indicating statistical significance or results in research contexts

academic and scientific writing

No Comments

No Known Activations