INDEX

Explanations

specific nouns and their associated descriptors across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

transQ

-0.60

featureID

-0.59

sidemargin

-0.57

SBATCH

-0.55

InitVars

-0.54

 vuitton

-0.54

Ɓ

-0.51

 internetowa

-0.50

 zwiſchen

-0.50

reactstrap

-0.50

POSITIVE LOGITS

 nécessairement

0.35

ंदीखरीदारी

0.33

Affirmed

0.31

mergeFrom

0.31

 exécu

0.31

ecutable

0.31

 poursuite

0.31

TProtocol

0.30

 overall

0.30

 общего

0.30

Activations Density 0.113%

specific nouns and their associated descriptors across various contexts

No Comments

No Known Activations