INDEX

Explanations

references to doors and their mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

󠁿

-0.83

liesslich

-0.81

"")

-0.80

anyahu

-0.79

 HasFactory

-0.78

']],

-0.78

 Palmas

-0.77

--

-0.76

")),

-0.74

)]$

-0.74

POSITIVE LOGITS

 doors

1.71

 door

1.64

 Doors

1.60

 Door

1.57

door

1.55

 DOOR

1.50

Door

1.45

Doors

1.42

doors

1.33

DOOR

1.18

Activations Density 0.056%

references to doors and their mechanisms

No Comments

No Known Activations