INDEX

Explanations

criteria for assessing perfect fits and comparisons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 kasarigan

-0.52

enumi

-0.45

cjs

-0.45

 Pinn

-0.45

"?>

-0.43

obi

-0.43

Geb

-0.41

 releg

-0.41

paravant

-0.40

 Gump

-0.39

POSITIVE LOGITS

 match

2.25

fit

1.95

match

1.93

 matches

1.87

 Match

1.83

 MATCH

1.82

Match

1.76

 matching

1.75

MATCH

1.64

Fit

1.61

Activations Density 0.273%

criteria for assessing perfect fits and comparisons in various contexts

No Comments

No Known Activations