INDEX

Explanations

references to specific programs or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 moreover

-0.94

何より

-0.93

むしろ

-0.90

 furthermore

-0.89

 therefore

-0.88

Поэтому

-0.87

 esimerkiksi

-0.81

 Apalagi

-0.81

 jopa

-0.81

 apalagi

-0.80

POSITIVE LOGITS

 Allí

0.88

 Prior

0.74

Its

0.74

该

0.72

该

0.71

Prior

0.71

 Briefly

0.71

Its

0.71

 autorytatywna

0.69

InjectAttribute

0.69

Activations Density 0.639%

references to specific programs or evaluations

No Comments

No Known Activations