INDEX

Explanations

references to charts and graphical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

+(-

-0.78

AlterField

-0.73

uinal

-0.72

 cherchés

-0.71

wnież

-0.71

remadura

-0.70

 Autorizaciones

-0.70

észetes

-0.69

tamol

-0.69

Extinguishing

-0.69

POSITIVE LOGITS

 chart

2.47

 charts

2.42

 Chart

2.36

Chart

2.22

chart

2.21

 Charts

2.16

 CHART

1.96

charts

1.88

Charts

1.87

CHART

1.68

Activations Density 0.110%

references to charts and graphical representations

No Comments

No Known Activations