INDEX

Explanations

references to specific individuals and their associated attributes or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</b>

-0.92

 Bock

-0.86

 Siva

-0.85

Jax

-0.78

 Helga

-0.77

 Rade

-0.76

 دا

-0.73

hå

-0.71

<b>

-0.70

Schwe

-0.70

POSITIVE LOGITS

+#+#

0.94

mobileqq

0.91

CFP

0.90

fileID

0.88

SequentialGroup

0.86

RegistryLite

0.85

XmlAccessType

0.84

 Otis

0.84

 répon

0.83

ksesta

0.83

Activations Density 2.306%

references to specific individuals and their associated attributes or actions

No Comments

No Known Activations