INDEX

Explanations

the beginning of sections or paragraphs, indicated by specific markers or tokens

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

//});

-0.67

 مشين

-0.65

AutoScaleMode

-0.63

__).

-0.63

())));

-0.62

"></

-0.59

]++;

-0.58

).</

-0.57

SizeMode

-0.57

itonitis

-0.56

POSITIVE LOGITS

Tembelea

0.79

rungsseite

0.59

ResponseWriter

0.56

Kjelder

0.56

moveToFirst

0.54

Personendaten

0.53

gyen

0.51

featureID

0.48

ServletException

0.47

#+#

0.47

Activations Density 0.105%

the beginning of sections or paragraphs, indicated by specific markers or tokens

No Comments

No Known Activations