INDEX

Explanations

dates and references to specific days

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

EDEFAULT

-0.81

 تضيفلها

-0.81

 ProtoMessage

-0.70

rmtree

-0.69

 estoppel

-0.69

ervlak

-0.69

Lik

-0.68

Sas

-0.68

Composable

-0.67

Lik

-0.67

POSITIVE LOGITS

 February

2.14

February

1.92

 FEBRUARY

1.78

 Februar

1.76

FEBRUARY

1.68

Feb

1.67

 february

1.54

Feb

1.52

 februari

1.50

 Februari

1.49

Activations Density 0.079%

dates and references to specific days

No Comments

No Known Activations