INDEX

Explanations

words related to data types and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

期刊论文

-0.88

__":

-0.84

RegistryLite

-0.80

 Roskov

-0.76

Personensuche

-0.76

GEBURTSDATUM

-0.75

__':

-0.75

 Baillargeon

-0.71

horabuena

-0.71

__":

-0.70

POSITIVE LOGITS

CL

1.09

Cl

1.08

cl

1.05

Cla

0.93

Kl

0.88

Clu

0.86

cl

0.84

cls

0.84

cli

0.84

Clo

0.84

Activations Density 0.392%

words related to data types and classifications

No Comments

No Known Activations