INDEX

Explanations

numerical references and variables used in mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Schä

-0.70

terday

-0.67

 iſt

-0.66

 Leite

-0.64

Recom

-0.64

 typer

-0.64

grou

-0.64

 Thayer

-0.63

 Euse

-0.63

obenz

-0.63

POSITIVE LOGITS

1.27

nnn

1.25

1.17

nnnn

1.08

nn

1.07

Cn

0.97

̀n

0.96

setN

0.91

Xn

0.91

Activations Density 0.286%

numerical references and variables used in mathematical expressions

No Comments

No Known Activations