INDEX

Explanations

references to orientation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

емым

-0.74

 Fonseca

-0.74

rawQuery

-0.71

 Goliath

-0.68

expandindo

-0.67

liath

-0.66

LogFactory

-0.66

Alison

-0.66

 HasFactory

-0.66

synaptic

-0.66

POSITIVE LOGITS

 orientation

2.17

 orientations

2.05

orientation

2.04

 Orientation

2.02

 ORIENT

1.99

Orientation

1.79

 orient

1.78

 oriented

1.75

orient

1.75

 Oriented

1.73

Activations Density 0.090%

references to orientation in various contexts

No Comments

No Known Activations