INDEX

Explanations

elements related to settings and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

oupe

-0.61

protoimpl

-0.58

fvar

-0.54

Rohy

-0.52

vertible

-0.52

таратура

-0.51

rehension

-0.51

 acert

-0.50

 tronic

-0.49

 trơn

-0.47

POSITIVE LOGITS

 priority

1.22

Priority

1.10

 Priority

1.08

priority

1.04

 prioriti

1.03

 prioritized

1.02

 priorité

0.99

 prioritise

0.97

 prioritize

0.95

 priorities

0.95

Activations Density 0.641%

elements related to settings and configurations

No Comments

No Known Activations