INDEX

Explanations

words expressing necessity or obligation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 GenerationType

-0.75

DockStyle

-0.68

errHandler

-0.67

SharedCtor

-0.64

ellschaft

-0.63

 might

-0.59

 serem

-0.57

might

-0.56

aarrggbb

-0.55

endphp

-0.54

POSITIVE LOGITS

 surely

1.05

 always

0.81

 therefore

0.80

 necessarily

0.79

 certainly

0.77

aches

0.76

 never

0.71

 ALWAYS

0.67

ering

0.67

 Surely

0.66

Activations Density 0.091%

words expressing necessity or obligation

No Comments

No Known Activations