INDEX

Explanations

terms related to features and feature selection 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 @ 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

PVA

-0.98

Alp

-0.91

 pregunto

-0.89

thschild

-0.88

 GenerationType

-0.87

ALP

-0.87

]^{-

-0.87

 kantoor

-0.86

ioutil

-0.85

idp

-0.84

POSITIVE LOGITS

 features

2.11

 feature

1.90

 Features

1.77

features

1.71

Features

1.71

 FEATURE

1.64

 Feature

1.60

Feature

1.56

feature

1.55

 FEATURES

1.54

Activations Density 0.051%

terms related to features and feature selection in various contexts

No Comments

No Known Activations