INDEX

Explanations

references to IP addresses and brain-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<eos>

-0.57

the

-0.56

 continuous

-0.53

 highly

-0.51

dii

-0.50

 continued

-0.49

зор

-0.48

OCC

-0.48

 most

-0.47

POSITIVE LOGITS

LookAnd

1.06

DockStyle

1.02

:✨

1.02

 Мексичка

0.99

+#+#

0.96

Brainz

0.93

 незавершена

0.90

 propOrder

0.89

InjectAttribute

0.89

 Switches

0.87

Activations Density 0.128%

references to IP addresses and brain-related terms

No Comments

No Known Activations