INDEX

Explanations

symbols and notations related to mathematical or scientific 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

RenderAtEndOf

-0.86

mybatisplus

-0.80

manta

-0.79

ntax

-0.76

 cráneo

-0.75

 heraus

-0.75

hydra

-0.73

 विश्वसनीयता

-0.73

\{\\

-0.72

 الرخصة

-0.72

POSITIVE LOGITS

circ

1.58

(°

1.04

 circ

0.89

 degrees

0.87

°

0.85

 Degrees

0.82

°°

0.79

 Circ

0.75

°)

0.74

°-

0.73

Activations Density 0.082%

symbols and notations related to mathematical or scientific expressions

No Comments

No Known Activations