INDEX

Explanations

references to names and affiliations in academic or professional contexts

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

 Majefty

-0.78

 Houſe

-0.78

Efq

-0.77

 Chriftian

-0.76

 Theſe

-0.75

 ſtate

-0.74

 houſe

-0.72

 pleaſure

-0.72

 myſelf

-0.71

 Diſ

-0.71

POSITIVE LOGITS

van

1.09

 Dutch

0.99

Van

0.94

Dutch

0.91

 dutch

0.84

Van

0.84

 Amsterdam

0.83

VAN

0.81

enoord

0.81

Netherlands

0.79

Activations Density 0.180%

references to names and affiliations in academic or professional contexts

No Comments

No Known Activations