INDEX

Explanations

terms related to processes and elements in a structured or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 cerâmica

-0.51

่

-0.49

 prêmio

-0.48

 cœurs

-0.48

 avesse

-0.48

 dieux

-0.46

 adopción

-0.45

 eventuali

-0.45

 capuz

-0.45

Bibliography

-0.45

POSITIVE LOGITS

ImageContext

1.15

 оригіналу

1.02

PreferredItem

0.97

AndEndTag

0.90

 autorytatywna

0.90

tanleria

0.88

DoubleQuotes

0.85

EndContext

0.83

NOPQRST

0.83

CodedInputStream

0.83

Activations Density 0.098%

terms related to processes and elements in a structured or technical context

No Comments

No Known Activations