INDEX

Explanations

sequences of tokens that represent programming constructs or elements structured in code-like formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Inscrivez

-0.51

 TÉCN

-0.48

Liefs

-0.47

 Democrá

-0.47

 Turquía

-0.47

 Comprometido

-0.45

 Gesetzes

-0.44

 Jurí

-0.44

 Keuangan

-0.44

 econó

-0.43

POSITIVE LOGITS

mybatisplus

0.80

 للاسماء

0.73

isation

0.67

+#+

0.61

ation

0.60

ment

0.59

Życiorys

0.59

burgh

0.58

atics

0.58

ization

0.58

Activations Density 1.060%

sequences of tokens that represent programming constructs or elements structured in code-like formatting

No Comments

No Known Activations