INDEX

Explanations

various programming constructs and syntax elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ―――――

-0.84

ſelf

-0.83

 iſt

-0.83

 itſelf

-0.82

 ་་

-0.81

 jsPsych

-0.81

 MainAxisSize

-0.80

ſelves

-0.80

 greateſt

-0.79

 pleaſure

-0.79

POSITIVE LOGITS

<eos>

0.68

0.55

in

0.53

un

0.52

 with

0.51

at

0.51

 these

0.50

co

0.50

be

0.49

 this

0.48

Activations Density 3.431%

various programming constructs and syntax elements in code

No Comments

No Known Activations