INDEX

Explanations

references to ties and tying in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Leandro

-0.89

PRD

-0.89

 Hän

-0.87

SharedCtor

-0.85

RegressionTest

-0.84

envolvimento

-0.83

minlength

-0.82

 Nemesis

-0.81

 Credo

-0.81

="#"><

-0.79

POSITIVE LOGITS

knot

0.89

Knot

0.85

 Knot

0.81

 knots

0.78

omitempty

0.74

Tie

0.73

 esti

0.71

 Stras

0.71

 tying

0.69

 Brace

0.67

Activations Density 0.439%

references to ties and tying in various contexts

No Comments

No Known Activations