INDEX

Explanations

references to pins and related concepts 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onCancelled

-0.75

ècie

-0.72

 ivelany

-0.70

PrototypeOf

-0.70

zzleHttp

-0.69

 karşılaş

-0.69

 jsonArray

-0.67

 Dietz

-0.67

apimachinery

-0.66

 تضيفلها

-0.65

POSITIVE LOGITS

pin

3.84

Pin

3.67

Pin

3.60

pin

3.43

 pins

3.13

PIN

2.96

PIN

2.89

pins

2.77

 Pins

2.73

 pinning

2.58

Activations Density 0.023%

references to pins and related concepts in various contexts

No Comments

No Known Activations