INDEX

Explanations

references to circular shapes and structures

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

legen

-0.59

 crystal

-0.58

申

-0.58

 xanth

-0.58

 тю

-0.55

 fusil

-0.55

 enhanced

-0.53

 embri

-0.53

ileo

-0.53

ricist

-0.53

POSITIVE LOGITS

gh

1.48

Gh

1.11

gh

1.03

 circular

1.00

 Circular

0.99

GH

0.98

ght

0.95

AGH

0.93

circular

0.93

ghs

0.91

Activations Density 0.425%

references to circular shapes and structures

No Comments

No Known Activations