INDEX

Explanations

numerical values associated with rates and their fluctuations

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

 Parsons

-0.82

jeg

-0.75

 Montserrat

-0.71

 onCreateView

-0.69

jib

-0.67

ellery

-0.66

")

-0.65

ogon

-0.64

Архівовано

-0.64

conj

-0.63

POSITIVE LOGITS

 rates

2.50

 rate

2.37

 Rate

2.24

 Rates

2.22

 RATE

2.16

Rate

2.10

Rates

2.08

 RATES

1.98

RATE

1.92

rate

1.92

Activations Density 0.088%

numerical values associated with rates and their fluctuations

No Comments

No Known Activations