INDEX

Explanations

specific references to information and data, particularly relating to permissions and details about abstract concepts or systems

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

oredCriteria

-0.44

лександр

-0.44

 sorte

-0.43

LookAnd

-0.43

merkung

-0.43

WithIOException

-0.43

-0.42

 transfieras

-0.42

volver

-0.41

padek

-0.41

POSITIVE LOGITS

 information

1.89

 informations

1.64

information

1.63

 info

1.54

 Information

1.51

Information

1.49

 INFORMATION

1.47

 información

1.38

INFORMATION

1.37

 informações

1.34

Activations Density 0.327%

specific references to information and data, particularly relating to permissions and details about abstract concepts or systems

No Comments

No Known Activations