INDEX

Explanations

references to technical expertise or roles

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

IndentedString

-0.82

omitempty

-0.80

InputBorder

-0.79

SBATCH

-0.78

kháu

-0.75

 StatefulWidget

-0.73

Oyo

-0.73

 Partager

-0.73

 disponibilités

-0.72

 OMIT

-0.72

POSITIVE LOGITS

 technical

3.14

 Technical

3.03

Technical

2.93

technical

2.80

 TECHNICAL

2.65

TECHNICAL

2.48

 teknis

2.04

 technische

2.00

 technischen

1.94

 technically

1.89

Activations Density 0.093%

references to technical expertise or roles

No Comments

No Known Activations