INDEX

Explanations

references to beds

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

the word "bed"

np_acts-logits-general · gemini-2.0-flash

bed as part of phrases

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Cyfeiriadau

-0.92

 smile

-0.81

 happiness

-0.81

happiness

-0.78

DockStyle

-0.75

Happiness

-0.71

MemoryWarning

-0.71

 smiles

-0.70

tvguidetime

-0.69

AsUp

-0.68

POSITIVE LOGITS

 Beds

1.07

 beds

1.05

Bed

0.96

beds

0.95

BED

0.93

Beds

0.92

Bed

0.90

BED

0.83

bed

0.80

 headboard

0.77

Activations Density 0.061%

references to beds

the word "bed"

bed as part of phrases

No Comments

No Known Activations