INDEX

Explanations

actions or events that signify the beginning or starting points of various processes

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

 nakalista

-0.69

出版年

-0.67

enumi

-0.66

 practised

-0.64

Portale

-0.61

NKC

-0.60

Sucesor

-0.60

 propOrder

-0.60

PhysRev

-0.60

 practiced

-0.60

POSITIVE LOGITS

 starts

1.61

 Starts

1.52

 begins

1.40

starts

1.27

Starts

1.26

begins

1.20

 Begins

1.18

 beginnt

1.08

 começa

1.07

 commences

1.07

Activations Density 0.164%

actions or events that signify the beginning or starting points of various processes

No Comments

No Known Activations