INDEX

Explanations

directional references related to positioning or layout

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XMLSchema

-0.66

 getItemCount

-0.62

 eventName

-0.61

PoolSize

-0.61

XmlEnum

-0.60

 Infórmanos

-0.60

ragamo

-0.60

 PeEnEo

-0.60

verifyException

-0.60

awtextra

-0.59

POSITIVE LOGITS

 left

1.83

left

1.80

Left

1.77

 Left

1.72

LEFT

1.48

 LEFT

1.48

 izquierdo

1.11

 izquierda

1.11

 esquerda

1.08

左

1.07

Activations Density 0.127%

directional references related to positioning or layout

No Comments

No Known Activations