INDEX

Explanations

the beginning of blocks of text or sections in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 COVID

-0.99

 https

-0.96

https

-0.88

 Covid

-0.85

 covid

-0.83

COVID

-0.79

covid

-0.77

 pandemic

-0.73

Covid

-0.71

POSITIVE LOGITS

 idéia

1.22

SourceChecksum

1.10

 definately

0.93

myspace

0.92

 Daß

0.88

 ModelExpression

0.83

berdayakan

0.82

WebControls

0.82

antMatchers

0.81

^_^

0.80

Activations Density 0.122%

the beginning of blocks of text or sections in a document

No Comments

No Known Activations