INDEX

Explanations

expressions related to boundaries and separations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

édrale

-0.55

Manbalar

-0.53

 intptr

-0.49

srcs

-0.48

WEBPACK

-0.47

bukkit

-0.47

aulted

-0.46

).—

-0.45

 AudioSource

-0.45

 autorytatywna

-0.44

POSITIVE LOGITS

 boundaries

1.99

 boundary

1.98

 borders

1.73

 Boundaries

1.68

 border

1.64

boundaries

1.60

boundary

1.58

 Boundary

1.54

Boundary

1.47

Boundaries

1.47

Activations Density 0.555%

expressions related to boundaries and separations

No Comments

No Known Activations