INDEX

Explanations

references to experts and expertise in various fields

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

TypedDataSet

-0.78

thâu

-0.78

 للاسماء

-0.74

łasz

-0.72

afone

-0.72

vaadin

-0.71

writerow

-0.71

 &___

-0.71

igerung

-0.70

urlopen

-0.69

POSITIVE LOGITS

 experts

2.08

 expert

2.07

 Expert

1.93

Expert

1.89

 Experts

1.85

expert

1.76

 EXPERT

1.76

Experts

1.74

experts

1.67

 expertise

1.60

Activations Density 0.058%

references to experts and expertise in various fields

No Comments

No Known Activations