INDEX

Explanations

phrases indicating possibility or potential outcomes

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

 sceptre

-0.70

 autorytatywna

-0.67

ed

-0.66

PerformLayout

-0.65

numerusform

-0.64

 enseña

-0.64

 Reyna

-0.62

 tobacco

-0.58

 Rhonda

-0.58

 cheia

-0.58

POSITIVE LOGITS

 Possibility

0.99

POSSIBLE

0.86

öglich

0.84

 Possibilities

0.84

 Möglich

0.82

 possibility

0.82

зможно

0.80

 possib

0.79

 POSS

0.78

Possibility

0.75

Activations Density 0.084%

phrases indicating possibility or potential outcomes

No Comments

No Known Activations