INDEX

Explanations

code snippets and programming logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 (...)

-0.59

 (…)

-0.58

 CanadaChoose

-0.55

ēju

-0.47

 Beit

-0.46

«,

-0.46

 Heil

-0.45

[…]

-0.45

bille

-0.45

Hu

-0.44

POSITIVE LOGITS

GEBURTSDATUM

0.91

########.

0.80

 defaultstate

0.80

ArrowToggle

0.80

}{@

0.75

 upto

0.75

లాలు

0.73

soever

0.73

complexContent

0.71

upto

0.71

Activations Density 0.061%

code snippets and programming logic

No Comments

No Known Activations