INDEX

Explanations

phrases related to selection criteria and ranges in data or experimental contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.52

TestBed

-0.49

LabelTagHelper

-0.49

ide

-0.42

 surla

-0.42

FormTagHelper

-0.41

 eventdata

-0.40

 FontWeight

-0.39

 xung

-0.39

TextBoxColumn

-0.38

POSITIVE LOGITS

 pleaſure

0.89

 ſtate

0.84

 ſmall

0.83

 Inſ

0.83

 quelcon

0.81

complexContent

0.80

 houſe

0.80

 ſche

0.79

 poffe

0.79

 fubject

0.79

Activations Density 0.583%

phrases related to selection criteria and ranges in data or experimental contexts

No Comments

No Known Activations