INDEX

Explanations

mathematical or structural expressions involving variables and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 betweenstory

-0.62

 kasarigan

-0.58

AndEndTag

-0.52

 tartalomajánló

-0.52

AddHtmlAttribute

-0.51

rån

-0.50

umably

-0.46

Dep

-0.45

fvar

-0.45

dep

-0.44

POSITIVE LOGITS

 pleaſure

0.85

ſelves

0.84

Controllo

0.83

Geplaatst

0.81

 Majefty

0.81

 themſelves

0.79

ſelf

0.79

 Moslem

0.78

 Jefus

0.78

 ſever

0.78

Activations Density 0.171%

mathematical or structural expressions involving variables and their relationships

No Comments

No Known Activations