INDEX

Explanations

references to ropes and their associated actions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 تانيه

-0.67

rrggbb

-0.66

 Fairchild

-0.66

Hochspringen

-0.64

 countenance

-0.62

 mugs

-0.61

Hozzáférés

-0.60

PRNewswire

-0.60

 flushed

-0.60

 muffin

-0.60

POSITIVE LOGITS

 rope

1.09

 Rope

0.97

 ropes

0.95

Rope

0.93

 cord

0.84

 cable

0.83

 string

0.81

 Cord

0.78

rope

0.77

 cables

0.76

Activations Density 0.553%

references to ropes and their associated actions or conditions

No Comments

No Known Activations