INDEX

Explanations

references to various models and their configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IBarButtonItem

-0.77

WebVitals

-0.67

achten

-0.67

Чу

-0.66

 intitulée

-0.64

Eup

-0.62

 divertidas

-0.61

SequentialGroup

-0.60

readdir

-0.60

FontAwesomeIcon

-0.60

POSITIVE LOGITS

 MODEL

1.72

 models

1.68

 model

1.67

 Model

1.66

 Models

1.51

model

1.50

Models

1.49

MODEL

1.47

Model

1.36

 MODELS

1.36

Activations Density 0.077%

references to various models and their configurations

No Comments

No Known Activations