INDEX

Explanations

numeric data and structure in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

########.

-1.03

StoryboardSegue

-0.98

 beginnetje

-0.94

 ComVisible

-0.94

 Мексичка

-0.92

 AssemblyCulture

-0.92

SequentialGroup

-0.92

AccessorTable

-0.91

GEBURTSDATUM

-0.88

XMLSchema

-0.85

POSITIVE LOGITS

employeeId

0.45

 титу

0.42

lichter

0.36

ID

0.36

 vše

0.35

aside

0.34

 चाहिए

0.34

 title

0.34

 Motta

0.33

 дерево

0.33

Activations Density 1.155%

numeric data and structure in the text

No Comments

No Known Activations