INDEX

Explanations

actions related to physical movement or positioning

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 estekak

-0.82

 autorytatywna

-0.82

 lenker

-0.76

 jLabel

-0.76

RectangleBorder

-0.75

WriteTagHelper

-0.72

AddTagHelper

-0.72

 CreateTagHelper

-0.69

AddHtmlAttribute

-0.68

UnusedPrivate

-0.68

POSITIVE LOGITS

set

1.00

cut

0.90

hit

0.90

 cast

0.85

 beat

0.82

put

0.76

 read

0.70

let

0.65

run

0.64

 spread

0.64

Activations Density 0.292%

actions related to physical movement or positioning

No Comments

No Known Activations