INDEX

Explanations

references to landscapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

findpost

-0.90

 vPvB

-0.70

@"/

-0.69

 besonder

-0.68

Tikang

-0.68

цездатний

-0.66

icoli

-0.63

 AssemblyCulture

-0.61

 мәкал

-0.61

PerformLayout

-0.59

POSITIVE LOGITS

 Inform

0.79

Inform

0.78

inform

0.77

 wide

0.77

 inform

0.76

 WIDE

0.76

 landscaping

0.64

wide

0.64

ush

0.61

 shared

0.61

Activations Density 0.142%

references to landscapes

No Comments

No Known Activations