INDEX

Explanations

terms related to plugins and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.71

Mau

-0.64

~*~

-0.64

Graeme

-0.64

<<<<<<<<

-0.63

removeAttr

-0.62

 Gray

-0.61

ocardium

-0.61

 Хи

-0.61

sstelle

-0.60

POSITIVE LOGITS

 Plug

1.59

 plug

1.58

plug

1.54

 plugs

1.53

plugs

1.43

Plug

1.42

 plugging

1.30

 PLUG

1.23

Plu

1.19

 plugged

1.18

Activations Density 0.104%

terms related to plugins and connections

No Comments

No Known Activations