INDEX

Explanations

proper nouns, especially names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

<eos>

-1.10

-0.92

↵

-0.75

...

-0.70

...

-0.69

-0.68

-0.66

↵↵

-0.66

POSITIVE LOGITS

Efq

1.63

ſelves

1.51

^(@)

1.45

 Jefus

1.44

 Majefty

1.43

ſelf

1.43

Personensuche

1.41

 autorytatywna

1.38

 myſelf

1.37

 doubtnut

1.33

Activations Density 1.625%

proper nouns, especially names and places

No Comments

No Known Activations