INDEX

Explanations

technical terms and specific identifiers related to programming, data types, and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

AccessorTable

-0.59

 Cochin

-0.59

utuhan

-0.59

 Mecca

-0.59

Efficiency

-0.58

VideoCapture

-0.57

 exciter

-0.57

DidChange

-0.56

clusal

-0.56

zensionen

-0.56

POSITIVE LOGITS

Rus

0.63

Rus

0.60

 Silver

0.58

expandindo

0.58

ston

0.56

anth

0.56

AndEndTag

0.56

AddTagHelper

0.55

Tembelea

0.55

 ку

0.54

Activations Density 2.448%

technical terms and specific identifiers related to programming, data types, and functions

No Comments

No Known Activations