INDEX

Explanations

programming or coding terminology, particularly within a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

Personendaten

-0.95

Tembelea

-0.85

 AssemblyCulture

-0.77

:+:

-0.77

PreInfinity

-0.76

 autorytatywna

-0.76

BeginContext

-0.76

ConstraintMaker

-0.75

 مرئيه

-0.74

 queſta

-0.73

POSITIVE LOGITS

 Rückkehr

0.42

判断

0.37

本

0.35

未

0.35

操作

0.34

新

0.34

外界

0.34

【

0.33

 råd

0.33

TODO

0.32

Activations Density 0.076%

programming or coding terminology, particularly within a structured context

No Comments

No Known Activations

programming or coding terminology, particularly within a structured context

No Comments

No Known Activations