INDEX

Explanations

references to various types of sources and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Tif

-0.86

 <>",

-0.84

AlterField

-0.81

beforeEach

-0.76

 flocc

-0.73

XmlAccessorType

-0.72

autoreleasepool

-0.70

 Akismet

-0.70

 QtWidgets

-0.69

shadowRadius

-0.69

POSITIVE LOGITS

 source

2.05

 SOURCE

1.99

 Source

1.94

 sources

1.87

Source

1.83

 Sources

1.75

source

1.72

setSource

1.68

Sources

1.59

sources

1.58

Activations Density 0.059%

references to various types of sources and their attributes

No Comments

No Known Activations