INDEX

Explanations

references to steps and tips in various contexts, indicating a focus on procedural guidance or advice

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

IUrlHelper

-0.62

 blessé

-0.55

}});

-0.53

 specchio

-0.53

 Azevedo

-0.52

TOXIC

-0.52

RegistryLite

-0.52

});

-0.51

 sepenuhnya

-0.51

 blessés

-0.50

POSITIVE LOGITS

 steps

1.08

 drops

1.03

 Steps

1.00

 bites

0.95

Steps

0.93

 tips

0.92

 breaks

0.91

 moves

0.89

 TIPS

0.89

 hits

0.86

Activations Density 0.166%

references to steps and tips in various contexts, indicating a focus on procedural guidance or advice

No Comments

No Known Activations