INDEX

Explanations

the term "ignore" in various contexts, indicating a focus on documentation or instructions regarding items to be omitted or disregarded

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Ruh

-0.84

 boissons

-0.78

ب

-0.77

EDS

-0.75

 titolata

-0.73

 états

-0.72

 piedi

-0.71

udah

-0.70

 colpa

-0.70

POSITIVE LOGITS

]--;

0.89

íso

0.83

bootstrapcdn

0.77

 Exor

0.73

etcode

0.73

lloworld

0.72

NORE

0.72

 Helper

0.71

ffix

0.70

icestershire

0.69

Activations Density 0.142%

the term "ignore" in various contexts, indicating a focus on documentation or instructions regarding items to be omitted or disregarded

No Comments

No Known Activations