INDEX

Explanations

mentions of various types of ropes and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 تانيه

-0.90

_{*}

-0.76

Portail

-0.76

lecteur

-0.75

 cheeks

-0.74

</tfoot>

-0.73

GEBURTSDATUM

-0.72

 Infórmanos

-0.71

참고

-0.71

BCG

-0.70

POSITIVE LOGITS

 rope

1.10

 ropes

1.04

 Rope

0.97

Rope

0.95

 knot

0.92

 knots

0.92

Knot

0.91

knot

0.90

 twine

0.90

 Knot

0.89

Activations Density 0.401%

mentions of various types of ropes and their interactions

No Comments

No Known Activations