INDEX

Explanations

references to signatures and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Ra

-0.72

ers

-0.71

 macchine

-0.67

-0.65

выше

-0.64

be

-0.64

 aDecoder

-0.63

 række

-0.63

so

-0.60

POSITIVE LOGITS

 pleaſure

1.19

 Savo

1.14

 Monfieur

1.07

 Majefty

1.07

Portail

1.07

 myſelf

1.06

 Chriftian

1.04

 triom

1.02

 viſ

1.00

 poffe

0.99

Activations Density 0.151%

references to signatures and related concepts

No Comments

No Known Activations