INDEX

Explanations

phrases indicating additional features, options, or numerous applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.94

ParallelGroup

-0.63

'}>

-0.59

',

-0.58

 LayoutInflater

-0.58

ollectionView

-0.58

'{@

-0.58

addPreferredGap

-0.58

ագրություններ

-0.58

intios

-0.57

POSITIVE LOGITS

0.68

등

0.62

etera

0.59

ifrance

0.58

lardır

0.53

راسیون

0.51

ktı

0.48

ühm

0.47

 McNeil

0.47

Activations Density 0.092%

phrases indicating additional features, options, or numerous applications

No Comments

No Known Activations