INDEX

Explanations

terms related to fast transformations or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

IsContent

-0.85

AddTagHelper

-0.84

featureID

-0.84

 يتيمه

-0.83

Personensuche

-0.82

ArrowToggle

-0.79

 utafitiHapana

-0.74

InputBorder

-0.74

queryInterface

-0.73

OGND

-0.73

POSITIVE LOGITS

 Fast

0.82

Fast

0.80

Deep

0.76

 Fine

0.75

Fine

0.71

 Deep

0.70

FAST

0.70

Good

0.69

Direct

0.69

Hard

0.68

Activations Density 0.554%

terms related to fast transformations or processes

No Comments

No Known Activations