INDEX

Explanations

references to feelings of loneliness or being alone

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

 judiciaire

-1.03

 EconPapers

-0.84

 StatelessWidget

-0.77

enumii

-0.76

 présidenti

-0.75

ArrowToggle

-0.74

 financières

-0.74

endphp

-0.74

Einzelnachweise

-0.72

IsMutable

-0.72

POSITIVE LOGITS

 clever

0.82

 simple

0.80

clever

0.76

simple

0.69

Tell

0.65

 Tell

0.64

 Simple

0.63

Clever

0.61

Portail

0.61

 Clever

0.58

Activations Density 0.169%

references to feelings of loneliness or being alone

No Comments

No Known Activations