INDEX

Explanations

references to directionality and spatial orientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

]--;

-1.14

GEBURTSDATUM

-1.04

abestanden

-0.99

 NSCoder

-0.98

-0.95

Espèce

-0.94

новниш

-0.93

 HasFactory

-0.91

]]);

-0.90

 bezeichneter

-0.88

POSITIVE LOGITS

 direction

1.65

 Direction

1.45

 directions

1.45

Direction

1.43

 DIRECTION

1.43

direction

1.36

DIRECTION

1.31

directions

1.17

 Directions

1.16

 DIRECTIONS

1.05

Activations Density 0.094%

references to directionality and spatial orientation

No Comments

No Known Activations