INDEX

Explanations

references to plots or plot-related content in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Unmount

-0.80

 /\.(

-0.75

principalColumn

-0.75

IBarButtonItem

-0.74

CORBA

-0.72

CompilerServices

-0.72

shadowRadius

-0.71

GIVEREF

-0.71

 onCancelled

-0.70

حياتها

-0.70

POSITIVE LOGITS

 Plots

1.62

 PLOT

1.55

 plots

1.54

 plot

1.50

 Plot

1.48

plot

1.43

PLOT

1.34

Plot

1.32

Plots

1.30

plots

1.26

Activations Density 0.086%

references to plots or plot-related content in narratives

No Comments

No Known Activations