INDEX

Explanations

references to the name "Robins" and terms related to robotics

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Charlemagne

-0.94

 Cassel

-0.88

 Ters

-0.79

 jira

-0.78

 lepto

-0.77

 Mende

-0.75

 bershka

-0.75

Efq

-0.75

 pleaſure

-0.75

ESE

-0.74

POSITIVE LOGITS

 robot

1.39

 robots

1.30

 Robot

1.26

 Robots

1.23

Rob

1.21

Robot

1.16

robot

1.16

Robots

1.14

obot

1.13

 robo

1.11

Activations Density 0.010%

references to the name "Robins" and terms related to robotics

No Comments

No Known Activations