INDEX

Explanations

references to unknown entities or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

QMetaType

-0.75

 Dempsey

-0.57

WithIOException

-0.55

@"/

-0.55

 indefinite

-0.54

 AssemblyVersion

-0.52

itoria

-0.51

WriteTagHelper

-0.51

Emission

-0.49

AddTagHelper

-0.49

POSITIVE LOGITS

 knowledge

1.94

know

1.84

 know

1.75

Know

1.71

 Know

1.69

 unknown

1.64

knowledge

1.63

 Unknown

1.58

KNOW

1.57

unknown

1.51

Activations Density 0.102%

references to unknown entities or information

No Comments

No Known Activations