INDEX

Explanations

terms related to statistical methods or analysis

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

UserScript

-0.76

/*

-0.71

 Anſ

-0.69

 ſhould

-0.69

 Theſe

-0.69

 Fukushima

-0.67

 TreeNode

-0.66

 ModelExpression

-0.66

 Tango

-0.65

 lara

-0.65

POSITIVE LOGITS

st

2.96

st

2.37

ST

2.17

ST

1.80

St

1.60

St

1.48

sts

1.42

stt

1.15

rst

1.12

 ст

1.11

Activations Density 0.057%

terms related to statistical methods or analysis

No Comments

No Known Activations