INDEX

Explanations

code-related terms and specific data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.52

</blockquote>

-0.45

-0.44

-0.41

-0.39

____________

-0.39

................

-0.38

]));

-0.38

POSITIVE LOGITS

rungsseite

1.18

tvguidetime

1.05

PerformLayout

0.99

 lenker

0.98

ArgsConstructor

0.95

GraphicsUnit

0.94

 виправивши

0.93

 ISNI

0.90

 مشين

0.88

 beginnetje

0.87

Activations Density 0.425%

code-related terms and specific data structures

No Comments

No Known Activations