INDEX

Explanations

references to different types of models in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

achten

-0.72

Чу

-0.68

Eup

-0.63

uptime

-0.63

WebVitals

-0.63

 Kear

-0.61

doPost

-0.61

 Susie

-0.61

 gulp

-0.61

IBarButtonItem

-0.60

POSITIVE LOGITS

 MODEL

1.85

 model

1.80

 Model

1.79

 models

1.77

model

1.63

 Models

1.61

MODEL

1.60

Models

1.52

Model

1.49

 MODELS

1.45

Activations Density 0.072%

references to different types of models in a technical context

No Comments

No Known Activations