INDEX

Explanations

the prefix "pre-" indicating something that occurs beforehand or in preparation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 ffilmiau

-0.68

KommentareTeilen

-0.64

sqcup

-0.63

TypedDataSet

-0.62

Enllaces

-0.62

niosek

-0.62

Опис

-0.62

 pouss

-0.62

$}}

-0.62

 LCCN

-0.61

POSITIVE LOGITS

pre

3.75

Pre

3.29

Pre

3.26

pre

3.10

PRE

2.78

PRE

2.66

 pré

2.58

预

1.99

 Pré

1.97

Pré

1.90

Activations Density 0.063%

the prefix "pre-" indicating something that occurs beforehand or in preparation

No Comments

No Known Activations

the prefix "pre-" indicating something that occurs beforehand or in preparation

No Comments

No Known Activations