INDEX

Explanations

words related to fastening or securing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 EconPapers

-0.73

SourceChecksum

-0.69

tande

-0.61

🤣🤣

-0.61

Ndr

-0.57

ValueStyle

-0.57

 Carr

-0.56

,&

-0.55

 perd

-0.53

 Verfügung

-0.53

POSITIVE LOGITS

 pins

1.36

 Pins

1.33

 pinning

1.31

pin

1.22

Pins

1.21

 pinned

1.20

Pin

1.20

Pin

1.10

pins

1.07

PIN

1.05

Activations Density 0.371%

words related to fastening or securing items

No Comments

No Known Activations