INDEX

Explanations

assertions about potential outcomes or characteristics related to entities or events

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

 Meksiku

-0.39

 Walkover

-0.38

RTSN

-0.36

baguna

-0.36

Gruss

-0.36

同志

-0.35

cellona

-0.35

UpdateCommand

-0.35

Instantiate

-0.35

 проду

-0.35

POSITIVE LOGITS

principalColumn

0.65

 ब्रेकडाउन

0.57

 للمعارف

0.56

ConstraintMaker

0.56

GOTREF

0.54

Portail

0.52

 esternos

0.52

WriteTagHelper

0.50

 NSCoder

0.50

 تضيفلها

0.50

Activations Density 0.069%

assertions about potential outcomes or characteristics related to entities or events

No Comments

No Known Activations